HugoEXPECTATIONPersonalized Explainable AI for decentralized agents with heterogeneous knowledge2024-03-07T14:19:37+00:00Giovanni Ciattogiovanni.ciatto@unibo.ithttps://expectation.ehealth.hevs.ch/Project Abstracthttps://expectation.ehealth.hevs.ch/posts/home/Giovanni Ciatto2021-07-01T00:00:00+01:002022-04-08T15:38:05+02:00
<!-- ![Expectation Logo](/full_expectation_logo.svg) -->
<!-- </br> -->
<p align="justify">Explainable AI (XAI) has recently emerged proposing a set of techniques attempting to explain machine learning (ML) models.
The recipients (explainee) are intended to be humans or other intelligent virtual entities. Transparency, trust, and debuging are the underlying features calling for XAI.
However, in real-world settings, systems are distributed, data are heterogeneous, the “system” knowledge is bounded, and privacy concerns are subject to variable constraints.
Current XAI approaches cannot cope with such requirements.
Therefore, there is a need for personalized explainable artificial intelligence. We plan to develop models and mechanisms to reconcile sub-symbolic, symbolic, and semantic representations leveraging on the agent-based paradigm.
In particular, the proposed approach combines inter-agent, intra-agent, and human-agent interactions to benefit from both the specialization of ML agents and the establishment of agent collaboration mechanisms, which will integrate heterogeneous knowledge/explanations extracted from efficient black-box AI agents.
The project includes the validation of the personalization and heterogeneous knowledge integration approach through a prototype application in the domain of food and nutrition monitoring and recommendation, including the evaluation of agent-human explainability, and the performance of the employed techniques in a collaborative AI environment.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="funded-by-chist-era"
>
Funded by CHIST-ERA
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/home/#funded-by-chist-era" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Funded by CHIST-ERA" href="#funded-by-chist-era">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<!-- <figure><img src="/chistera_logo.png"/>
</figure>
-->
<p><img
src="/chistera_logo.png"
alt="CHIST-ERA Logo"
/></p>
The Consortiumhttps://expectation.ehealth.hevs.ch/posts/consortium/Giovanni Ciatto2021-07-01T00:00:00+01:002022-09-12T15:06:25+02:00
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/hesso_logo.png"
alt="HES-SO Logo" /></p>
<div class="card-body" align="center"><p><b>HES-SO</b></p>
<p>University of Applied Sciences and Arts Western Switzerland</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.hevs.ch/en/minisites/projects-products/aislab/"
>
Find out more!
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/unibo_logo.png"
alt="UNIBO Logo" /></p>
<div class="card-body" align="center"><p><b>UNIBO</b></p>
<p>Alma Mater Studiorum Università di Bologna</p>
</br>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="http://expectation.apice.unibo.it/"
>
Find out more!
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/unilu_logo.png"
alt="UNILU Logo" /></p>
<div class="card-body" align="center"><p><b>UNILU</b></p>
<p>University of Luxembourg</p>
</br>
</br>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://wwwen.uni.lu/"
>
Find out more!
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/ozu_logo.png"
alt="OZU Logo" /></p>
<div class="card-body" align="center"><p><b>OZU</b></p>
<p>Özyeğin University</p>
</br>
</br>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.ozyegin.edu.tr/en"
>
Find out more!
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/list_logo.jpg"
alt="LIST Logo" /></p>
<div class="card-body" align="center"><p><b>LIST</b></p>
<p>Luxembourg Institute of Science and Technology</p>
</br>
</br>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.list.lu/"
>
Find out more!
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
</div>
Promohttps://expectation.ehealth.hevs.ch/posts/promo/Giovanni Ciatto2021-07-04T00:00:00+01:002022-12-14T16:17:28+01:00
<div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;">
<iframe src="https://www.youtube.com/embed/4quzI5_Y8R4" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" allowfullscreen title="YouTube Video"></iframe>
</div>
</br>
<div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;">
<iframe src="https://www.youtube.com/embed/V-N84DSitB4" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" allowfullscreen title="YouTube Video"></iframe>
</div>
A proud team!https://expectation.ehealth.hevs.ch/posts/people/Giovanni Ciatto2021-07-04T00:00:00+01:002023-10-11T10:23:12+02:00
<p>The team has multidisciplinary competences sharing the Multi-Agent Systems as common thread.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="hes-so-people-from-switzerland"
>
HES-SO People (from Switzerland)
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/people/#hes-so-people-from-switzerland" class="gblog-post__anchor clip flex align-center" aria-label="Anchor HES-SO People (from Switzerland)" href="#hes-so-people-from-switzerland">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/ms.jpg"
alt="Michael I. Schumacher Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Prof.</em> Michael I. Schumacher</strong></p>
<p>Full Professor at HES-SO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.linkedin.com/in/michael-ignaz-schumacher/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/dc.jpg"
alt="Davide Calvaresi Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Dr.</em> Davide Calvaresi</strong></p>
<p>Senior researcher at HES-SO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="http://davidecalvaresi.it"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/jpc.jpg"
alt="Jean-Paul Calbimonte Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Dr.</em> Jean-Paul Calbimonte</strong></p>
<p>Senior researcher at HES-SO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://jeanpi.org/wp/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/vh.jpg"
alt="Victor Hugo Contreras Ordonez Photo" /></p>
<div class="card-body" align="center"><p><strong>Victor Hugo Contreras Ordonez</strong></p>
<p>PhD Student at HES-SO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="#"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="unibo-people-from-italy"
>
UNIBO People (from Italy)
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/people/#unibo-people-from-italy" class="gblog-post__anchor clip flex align-center" aria-label="Anchor UNIBO People (from Italy)" href="#unibo-people-from-italy">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/ao.jpg"
alt="Andrea Omicini Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Prof.</em> Andrea Omicini</strong></p>
<p>Full Professor at UNIBO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.unibo.it/sitoweb/andrea.omicini"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/gc.jpg"
alt="Giovanni Ciatto Photo" /></p>
<div class="card-body" align="center"><p><strong>Giovanni Ciatto</strong></p>
<p>Post-doctoral Research Fellow at UNIBO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://about.me/gciatto"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/aa.jpg"
alt="Andrea Agiollo Photo" /></p>
<div class="card-body" align="center"><p><strong>Andrea Agiollo</strong></p>
<p>PhD Student at UNIBO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://apice.unibo.it/xwiki/bin/view/AndreaAgiollo/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/fs.jpg"
alt="Federico Sabbatini Photo" /></p>
<div class="card-body" align="center"><p><strong>Federico Sabbatini</strong></p>
<p>Research Fellow at UNIBO (up to Oct. 2021)</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://apice.unibo.it/xwiki/bin/view/FedericoSabbatini/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/mm.jpg"
alt="Matteo Magnini's Photo" /></p>
<div class="card-body" align="center"><p><strong>Matteo Magnini</strong></p>
<p>Research Fellow at UNIBO</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://apice.unibo.it/xwiki/bin/view/MatteoMagnini/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="unilu-people-from-luxemburg"
>
UNILU People (from Luxemburg)
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/people/#unilu-people-from-luxemburg" class="gblog-post__anchor clip flex align-center" aria-label="Anchor UNILU People (from Luxemburg)" href="#unilu-people-from-luxemburg">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/lvdt.jpg"
alt="Leon Van der Torre Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Prof.</em> Leon Van der Torre</strong></p>
<p>Full Professor at UNILU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://icr.uni.lu/leonvandertorre"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/jh.jpg"
alt="Joris Hulstijn's Photo" /></p>
<div class="card-body" align="center"><p><strong>Joris Hulstijn</strong></p>
<p>Researcher Responsible AI</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.linkedin.com/in/jorishulstijn/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/it.jpg"
alt="Igor Tchappi's Photo" /></p>
<div class="card-body" align="center"><p><strong>Igor Tchappi</strong></p>
<p>Research Associate</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.linkedin.com/in/igor-tchappi-b479b61a6"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="list-people-from-luxemburg"
>
LIST People (from Luxemburg)
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/people/#list-people-from-luxemburg" class="gblog-post__anchor clip flex align-center" aria-label="Anchor LIST People (from Luxemburg)" href="#list-people-from-luxemburg">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/an.jpg"
alt="Amro Najjar Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Dr.</em> Amro Najjar</strong></p>
<p>Full time researcher at LIST</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://wwwen.uni.lu/recherche/fstm/dcs/members/amro_najjar"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="ozu-people"
>
OZU People
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/people/#ozu-people" class="gblog-post__anchor clip flex align-center" aria-label="Anchor OZU People" href="#ozu-people">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="gblog-columns gblog-columns--regular flex flex-gap flex-mobile-column">
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/ra.jpg"
alt="Reyhan Aydoğan's Photo" /></p>
<div class="card-body" align="center"><p><strong><em>Prof.</em> Reyhan Aydoğan</strong></p>
<p>Professor at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://faculty.ozyegin.edu.tr/reyhanaydogan/"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/ad.jpg"
alt="Anil Dogru Photo" /></p>
<div class="card-body" align="center"><p><strong>Anil Dogru</strong></p>
<p>PhD Student at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://tr.linkedin.com/in/aniltrue"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/bk.jpg"
alt="Berkecan Kocyigit Photo" /></p>
<div class="card-body" align="center"><p><strong>Berkecan Kocyigit</strong></p>
<p>Master’s Student at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://intelisys.ozyegin.edu.tr/node/282"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/ek.jpg"
alt="Emre Kuru Photo" /></p>
<div class="card-body" align="center"><p><strong>Emre Kuru</strong></p>
<p>Bachelor’s Student at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://tr.linkedin.com/in/emre-kuru-35a178223"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/fc.jpg"
alt="Furkan Canturk Photo" /></p>
<div class="card-body" align="center"><p>(Formerly)</p>
<p><strong>Furkan Canturk</strong></p>
<p>Master’s Student at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.linkedin.com/in/furkan-canturk"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
<div class="card">
<p><img class="card-img-top"
src="/people/bb.jpg"
alt="Berk Buzcu Photo" /></p>
<div class="card-body" align="center"><p>(Formerly)</p>
<p><strong>Berk Buzcu</strong></p>
<p>Master’s Student at OZU</p>
</div>
<div class="card-footer" align="center"><span class="gblog-button gblog-button--regular">
<a
class="gblog-button__link" href="https://www.researchgate.net/profile/Berk_Buzcu"
>
Personal Homepage
</a>
</span>
</div>
</div>
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
<div class="gblog-columns__content gblog-markdown--nested flex-even">
</div>
</div>
Deliverableshttps://expectation.ehealth.hevs.ch/posts/deliverables/Giovanni Ciatto2022-04-08T00:00:00+01:002022-04-08T16:12:52+02:00
<div class="gblog-post__anchorwrap">
<h2 id="year-1"
>
Year 1
</h2>
</div>
<ul>
<li><strong>[D1.4]</strong> <a
class="gblog-markdown__link"
href="/deliverables/1.4.pdf"
>Data Management Plan</a> (DMP)</li>
<li><strong>[D2.1]</strong> <a
class="gblog-markdown__link"
href="/deliverables/2.1.pdf"
>Tech report on symbolic knowledge extraction and injection</a></li>
<li><strong>[D2.2]</strong> <a
class="gblog-markdown__link"
href="/deliverables/2.2.pdf"
>Scientific paper on symbolic knowledge extraction and injection</a></li>
<li><strong>[D2.3]</strong> <a
class="gblog-markdown__link"
href="/deliverables/2.3.pdf"
>Software libraries supporting extraction and injection</a></li>
</ul>
Expectation: Personalized Explainable Artificial Intelligence for Decentralized Agents with Heterogeneous Knowledge
https://expectation.ehealth.hevs.ch/posts/publications/ccnavos-extraamas-2021-expectation/Amro NajjarAndrea OmiciniDavide CalvaresiGiovanni CiattoLeon Van der TorreMichael I. SchumacherReyhan Aydoğan2021-07-04T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a>, <a href="mailto:leon.vandertorre@uni.lu">Leon Van der Torre</a>, <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a>, and <a href="mailto:michael.schumacher@hevs.ch">Michael I. Schumacher</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ccnavos-extraamas-2021-expectation/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Explainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret and explain machine learning (ML) predictors.
To date, many initiatives have been proposed.
Nevertheless, current research efforts mainly focus on methods tailored to specific ML tasks and algorithms, such as image classification and sentiment analysis.
However, explanation techniques are still embryotic, and they target principally ML experts rather than heterogeneous end-users.
Furthermore, existing solutions assume data to be centralized, homogeneous, and fully/continuously accessible, a situation which rarely holds in practice.
Arguably, a system-wide perspective is currently missing.
The project named “Personalized Explainable Artificial Intelligence for Decentralized Agents with Heterogeneous Knowledge” (Expectation) aims at overcoming such limitations.
This manuscript presents the overall objectives and approach of the Expectation project, focusing on advancing both theoretically and practically the state of the art of XAI towards the construction of personalized explanations in spite of decentralization and heterogeneity of knowledge, agents, and explainee (both humans or virtual).
To tackle the challenges posed by personalization, decentralization, and heterogeneity, the project fruitfully combines abstractions, methods, and approaches from the multi-agent systems, knowledge extraction and injection, negotiation, argumentation, and symbolic reasoning communities.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ccnavos-extraamas-2021-expectation/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-030-82017-6_20">https://doi.org/10.1007/978-3-030-82017-6_20</a></li>
<li>Preprint: <a href="https://apice.unibo.it/xwiki/bin/download/Publications/ExpectationExtraamas2021/extraamas-2021-expectation.pdf">https://apice.unibo.it/xwiki/bin/download/Publications/ExpectationExtraamas2021/extraamas-2021-expectation.pdf</a></li>
<li>Research Gate: <a href="https://www.researchgate.net/publication/353290416_Expectation_Personalized_Explainable_Artificial_Intelligence_for_Decentralized_Agents_with_Heterogeneous_Knowledge">https://www.researchgate.net/publication/353290416_Expectation_Personalized_Explainable_Artificial_Intelligence_for_Decentralized_Agents_with_Heterogeneous_Knowledge</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ccnavos-extraamas-2021-expectation/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ccnavos-extraamas-2021-expectation/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">expectation-extraamas2021</span><span class="p">,</span>
<span class="na">address</span> <span class="p">=</span> <span class="s">{Basel, Switzerland}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Ciatto, Giovanni and Najjar, Amro and Aydo{\u g}an, Reyhan and Van der Torre, Leon and Omicini, Andrea and Schumacher, Michael}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems. Third International Workshop, EXTRAAMAS 2021, Virtual Event, May 3--7, 2021, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-030-82017-6_20}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Fr{\"a}mling, Kary}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-030-82016-9}</span><span class="p">,</span>
<span class="na">isbn-online</span> <span class="p">=</span> <span class="s">{978-3-030-82017-6}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Multi-agent systems; eXplanable AI; Chist-Era IV; Personalisation; Decentralisation; Expectation}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{331--343}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Nature}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{Lecture Notes in Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{{{\sc Expectation}}: Personalized Explainable Artificial Intelligence for Decentralized Agents with Heterogeneous Knowledge}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-030-82017-6_20}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">12688</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
Towards Explainable Visionary Agents: License to Dare and Imagine
https://expectation.ehealth.hevs.ch/posts/publications/cncc-extraamas-2021-imagination/Amro NajjarDavide CalvaresiGiovanni CiattoJean-Paul Calbimonte2021-07-04T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, <a href="mailto:jean-paul.calbimonte@hevs.ch">Jean-Paul Calbimonte</a>, and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cncc-extraamas-2021-imagination/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue.
Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and their developers' capability of tailoring smart behaviors on the particular application domain(s).
However, to forecast all possible scenarios’ evolutions is unfeasible.
Thus, intelligent agents should autonomously/creatively adapt to the world’s mutability.
This paper investigates the meaning of imagination in the context of cognitive agents, addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges.
In particular, we investigated research areas such as: i) reasoning and automatic theorem proving (which is exploited to synthesize novel knowledge via inference), ii) automatic planning and simulation (which is exploited to speculate over alternative courses of action), iii) machine learning and data mining (which are exploited to induce new knowledge from experience), and (iv) biochemical coordination (which keeps imagination dynamic by continuously reorganizing it).</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cncc-extraamas-2021-imagination/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-030-82017-6_9">https://doi.org/10.1007/978-3-030-82017-6_9</a></li>
<li>Preprint: <a href="https://apice.unibo.it/xwiki/bin/download/Publications/ImaginationExtraamas2021/extraamas-2021-imagination.pdf">https://apice.unibo.it/xwiki/bin/download/Publications/ImaginationExtraamas2021/extraamas-2021-imagination.pdf</a></li>
<li>Research Gate: <a href="https://www.researchgate.net/publication/353292042_Towards_Explainable_Visionary_Agents_License_to_Dare_and_Imagine">https://www.researchgate.net/publication/353292042_Towards_Explainable_Visionary_Agents_License_to_Dare_and_Imagine</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cncc-extraamas-2021-imagination/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cncc-extraamas-2021-imagination/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">imagination-extraamas2021</span><span class="p">,</span>
<span class="na">address</span> <span class="p">=</span> <span class="s">{Basel, Switzerland}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Ciatto, Giovanni and Najjar, Amro and Calbimonte, Jean-Paul and Calvaresi, Davide}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems. Third International Workshop, EXTRAAMAS 2021, Virtual Event, May 3--7, 2021, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-030-82017-6_9}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Fr{\"a}mling, Kary}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-030-82016-9}</span><span class="p">,</span>
<span class="na">isbn-online</span> <span class="p">=</span> <span class="s">{978-3-030-82017-6}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Multi-agent systems; Imagination; BDI; Cognitive agents; XAI}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{139--157}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Nature}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{Lecture Notes in Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Towards Explainable Visionary Agents: License to Dare and Imagine}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-030-82017-6_9}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">12688</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span><span class="p">}</span>
</code></pre></div>
Shallow2Deep: Restraining Neural Networks Opacity through Neural Architecture Search
https://expectation.ehealth.hevs.ch/posts/publications/aco-extraamas-2021-shallo2deep/Andrea AgiolloAndrea OmiciniGiovanni Ciatto2021-07-04T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:andrea.agiollo@unibo.it">Andrea Agiollo</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-extraamas-2021-shallo2deep/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Recently, the Deep Learning (DL) research community has focused on developing efficient and highly performing Neural Networks (NN).
Meanwhile, the eXplainable AI (XAI) research community has focused on making Machine Learning (ML) and Deep Learning methods interpretable and transparent, seeking explainability.
This work is a preliminary study on the applicability of Neural Architecture Search (NAS) (a sub-field of DL looking for automatic design of NN structures) in XAI.
We propose Shallow2Deep, an evolutionary NAS algorithm that exploits local variability to restrain opacity of DL-systems through NN architectures simplification.
Shallow2Deep effectively reduces NN complexity – therefore their opacity – while reaching state-of-the-art performances. Unlike its competitors, Shallow2Deep promotes variability of localised structures in NN, helping to reduce NN opacity.
The proposed work analyses the role of local variability in NN architectures design, presenting experimental results that show how this feature is actually desirable.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-extraamas-2021-shallo2deep/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-030-82017-6_5">https://doi.org/10.1007/978-3-030-82017-6_5</a></li>
<li>Preprint: <a href="https://apice.unibo.it/xwiki/bin/download/Publications/Shallow2deepExtraamas2021/extraamas-2021-s2d.pdf">https://apice.unibo.it/xwiki/bin/download/Publications/Shallow2deepExtraamas2021/extraamas-2021-s2d.pdf</a></li>
<li>Research Gate: <a href="https://www.researchgate.net/publication/353314830_Shallow2Deep_Restraining_Neural_Networks_Opacity_Through_Neural_Architecture_Search">https://www.researchgate.net/publication/353314830_Shallow2Deep_Restraining_Neural_Networks_Opacity_Through_Neural_Architecture_Search</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-extraamas-2021-shallo2deep/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-extraamas-2021-shallo2deep/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">shallow2deep-extraamas2021</span><span class="p">,</span>
<span class="na">address</span> <span class="p">=</span> <span class="s">{Basel, Switzerland}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Agiollo, Ansdrea and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems. Third International Workshop, EXTRAAMAS 2021, Virtual Event, May 3--7, 2021, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-030-82017-6_5}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Fr{\"a}mling, Kary}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-030-82016-9}</span><span class="p">,</span>
<span class="na">isbn-online</span> <span class="p">=</span> <span class="s">{978-3-030-82017-6}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Neural Architecture Search; Evolutionary Algorithm; Opacity; Interpretability}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{63--82}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Nature}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{Lecture Notes in Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{{\it Shallow2Deep}: Restraining Neural Networks Opacity through Neural Architecture Search}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-030-82017-6_5}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">12688</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
Logic Programming library for Machine Learning: API design and prototype
https://expectation.ehealth.hevs.ch/posts/publications/logicapiml-cilc2022/Giovanni CiattoRoberta Calegari2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, Matteo Castigliò, and <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/logicapiml-cilc2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">In this paper we address the problem of hybridising symbolic and sub-symbolic approaches in artificial intelligence, following the purpose of creating flexible and data-driven systems, which are simultaneously comprehensible and capable of automated learning. In particular, we propose a logic API for supervised machine learning, enabling logic programmers to exploit neural networks – among the others – in their programs. Accordingly, we discuss the design and architecture of a library reifying APIs for the Prolog language in the 2P-Kt logic ecosystem. Finally, we discuss a number of snippets aimed at exemplifying the major benefits of our approach when designing hybrid systems.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/logicapiml-cilc2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-3204/paper_12.pdf">http://ceur-ws.org/Vol-3204/paper_12.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/logicapiml-cilc2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/logicapiml-cilc2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">logicapiml-cilc2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Ciatto, Giovanni and Castigliò, Matteo and Calegari, Roberta}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{CILC 2022 -- Italian Conference on Computational Logic}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{logic programming, machine learning, API, 2P-Kt}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">15</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{104--118}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{CEUR-WS}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{ceurws}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Logic Programming library for Machine Learning: {API} design and prototype}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_12.pdf}</span><span class="p">,</span>
<span class="na">urlopenaccess</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_12.pdf}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_12.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">3204</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors
https://expectation.ehealth.hevs.ch/posts/publications/sco-extraamas-2021-gridex/Andrea OmiciniFederico SabbatiniGiovanni Ciatto2021-07-04T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:f.sabbatini@unibo.it">Federico Sabbatini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/sco-extraamas-2021-gridex/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Knowledge extraction methods are applied to ML-based predictors to attain explainable representations of their functioning when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the extraction of either lists or trees of rules.
Yet, most of them only support supervised learning – and, in particular, classification – tasks. ITER is among the few rule extraction methods capable of extracting symbolic rules out of sub-symbolic regressors.
However, its performance – here intended as the interpretability of the rules it extracts – easily degrades as the complexity of the regression task at hand increases.
In this paper we propose GridEx, an extension of the ITER algorithm, aimed at extracting symbolic knowledge – in the form of lists of if-then-else rules – from any sort of sub-symbolic regressor—there including neural networks of arbitrary depth.
With respect to ITER, GridEx produces shorter rule lists retaining higher fidelity w.r.t. the original regressor.
Furthermore, to demonstrate the feasibility and effectiveness of GridEx, we report several experiments assessing its performance in comparison to both ITER and decision tree regressors, used as benchmarks.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/sco-extraamas-2021-gridex/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-030-82017-6_2">https://doi.org/10.1007/978-3-030-82017-6_2</a></li>
<li>Preprint: <a href="https://apice.unibo.it/xwiki/bin/download/Publications/GridExExtraamas2021/extraamas-2021-iter.pdf">https://apice.unibo.it/xwiki/bin/download/Publications/GridExExtraamas2021/extraamas-2021-iter.pdf</a></li>
<li>Research Gate: <a href="https://www.researchgate.net/publication/353295374_GridEx_An_Algorithm_for_Knowledge_Extraction_from_Black-Box_Regressors">https://www.researchgate.net/publication/353295374_GridEx_An_Algorithm_for_Knowledge_Extraction_from_Black-Box_Regressors</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/sco-extraamas-2021-gridex/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/sco-extraamas-2021-gridex/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">gridex-extraamas2021</span><span class="p">,</span>
<span class="na">address</span> <span class="p">=</span> <span class="s">{Basel, Switzerland}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Sabbatini, Federico and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems. Third International Workshop, EXTRAAMAS 2021, Virtual Event, May 3--7, 2021, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-030-82017-6_2}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Fr{\"a}mling, Kary}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-030-82016-9}</span><span class="p">,</span>
<span class="na">isbn-online</span> <span class="p">=</span> <span class="s">{978-3-030-82017-6}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">issn-online</span> <span class="p">=</span> <span class="s">{1611-3349}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{18--38}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Nature}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{Lecture Notes in Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{{GridEx}: An Algorithm for Knowledge Extraction from Black-Box Regressors}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-030-82017-6_2}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">12688</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
Graph Neural Networks as the Copula Mundi between Logic and Machine Learning: A Roadmap
https://expectation.ehealth.hevs.ch/posts/publications/aco-woa-2021-gnn/Andrea AgiolloAndrea OmiciniGiovanni Ciatto2021-10-07T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:andrea.agiollo@unibo.it">Andrea Agiollo</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-woa-2021-gnn/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Combining machine learning (ML) and computational logic (CL) is hard, mostly because of the inherently-different ways they use to represent knowledge. In fact, while ML relies on fixed-size numeric representations leveraging on vectors, matrices, or tensors of real numbers, CL relies on logic terms and clauses—which are unlimited in size and structure.
Graph neural networks (GNN) are a novelty in the ML world introduced for dealing with graph-structured data in a sub-symbolic way. In other words, GNN pave the way towards the application of ML to logic clauses and knowledge bases. However, there are several ways to encode logic knowledge into graphs: which is the best one heavily depends on the specific task at hand.
Accordingly, in this paper, we (i) elicit a number of problems from the field of CL that may benefit from many graph-related problems where GNN has been proved effective; (ii) exemplify the application of GNN to logic theories via an end-to-end toy example, to demonstrate the many intricacies hidden behind the technique; (iii) discuss the possible future directions of the application of GNN to CL in general, pointing out opportunities and open issues.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-woa-2021-gnn/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-2963/paper18.pdf">http://ceur-ws.org/Vol-2963/paper18.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-woa-2021-gnn/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aco-woa-2021-gnn/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">gnn-woa2021</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Agiollo, Andrea and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2021 -- 22nd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Denti, Enrico and Omicini, Andrea and Sartor, Giovanni}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Graph Neural Networks, Machine Learning, Embedding, Computational Logic}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">oct</span><span class="p">,</span>
<span class="na">note</span> <span class="p">=</span> <span class="s">{22nd Workshop ``From Objects to Agents'' (WOA 2021), Bologna, Italy, 1--3~}</span> <span class="p">#</span> <span class="nv">sep</span> <span class="p">#</span> <span class="s">{~2021. Proceedings}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">18</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{98--115}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Graph Neural Networks as the Copula Mundi between Logic and Machine Learning: A Roadmap}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-2963/paper18.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">2963</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
On the Design of PSyKE: A Platform for Symbolic Knowledge Extraction
https://expectation.ehealth.hevs.ch/posts/publications/scco-woa-2021-psyke/Andrea OmiciniFederico SabbatiniGiovanni CiattoRoberta Calegari2021-10-07T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:f.sabbatini@unibo.it">Federico Sabbatini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/scco-woa-2021-psyke/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-2963/paper14.pdf">http://ceur-ws.org/Vol-2963/paper14.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/scco-woa-2021-psyke/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">A common practice in modern explainable AI is to post-hoc explain black-box machine learning (ML) predictors – such as neural networks – by extracting symbolic knowledge out of them, in the form of either rule lists or decision trees. By acting as a surrogate model, the extracted knowledge aims at revealing the inner working of the black box, thus enabling its inspection, representation, and explanation.
Various knowledge-extraction algorithms have been presented in the literature so far. Unfortunately, running implementations of most of them are currently either proof of concepts or unavailable. In any case, a unified, coherent software framework supporting them all – as well as their interchange, comparison, and exploitation in arbitrary ML workflows – is currently missing.
Accordingly, in this paper we present the design of PSyKE, a platform providing general-purpose support to symbolic knowledge extraction from different sorts of black-box predictors via many extraction algorithms. Notably, PSyKE targets the extraction of symbolic knowledge in logic form, making it possible to extract first-order logic clauses as output. The extracted knowledge is thus both machine- and human- interpretable, and it can be used as a starting point for further symbolic processing—e.g. automated reasoning.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/scco-woa-2021-psyke/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/scco-woa-2021-psyke/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">psyke-woa2021</span><span class="p">,</span>
<span class="na">articleno</span> <span class="p">=</span> <span class="m">3</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Sabbatini, Federico and Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2021 -- 22nd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Denti, Enrico and Omicini, Andrea and Sartor, Giovanni}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{explainable AI, knowledge extraction, interpretable prediction, PSyKE}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">oct</span><span class="p">,</span>
<span class="na">note</span> <span class="p">=</span> <span class="s">{22nd Workshop ``From Objects to Agents'' (WOA 2021), Bologna, Italy, 1--3~}</span> <span class="p">#</span> <span class="nv">sep</span> <span class="p">#</span> <span class="s">{~2021. Proceedings}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">20</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{29--48}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{On the Design of {PSyKE}: A Platform for Symbolic Knowledge Extraction}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-2963/paper14.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">2963</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
2P-Kt: A Logic-Based Ecosystem for Symbolic AI
https://expectation.ehealth.hevs.ch/posts/publications/cco-softwarex-2021-2pkt/Andrea OmiciniGiovanni CiattoRoberta Calegari2021-10-07T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cco-softwarex-2021-2pkt/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">To date, logic-based technologies are either built on top or as extensions of the Prolog language, mostly working as monolithic solutions tailored upon specific inference procedures, unification mechanisms, or knowledge representation techniques. Instead, to maximise their impact, logic-based technologies should support and enable the general-purpose exploitation of all the manifold contributions from logic programming. Accordingly, we present 2P-Kt, a reboot of the tuProlog project offering a general, extensible, and interoperable ecosystem for logic programming and symbolic AI.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cco-softwarex-2021-2pkt/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1016/j.softx.2021.100817">https://doi.org/10.1016/j.softx.2021.100817</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cco-softwarex-2021-2pkt/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cco-softwarex-2021-2pkt/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">2pkt-swx16</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1016/j.softx.2021.100817}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{2352-7110}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{SoftwareX}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{logic programming, artificial intelligence, Prolog, Kotlin, tuProlog}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">dec</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{100817:1--7}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{{\textsf{2}P-Kt}: A Logic-Based Ecosystem for Symbolic {AI}}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://www.sciencedirect.com/science/article/pii/S2352711021001126}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">16</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
Towards cooperative argumentation for MAS: an Actor-based approach
https://expectation.ehealth.hevs.ch/posts/publications/pco-woa-2021-distributedarg/Andrea OmiciniGiuseppe PisanoRoberta Calegari2021-10-07T00:00:00+01:002022-04-08T15:38:05+02:00
<p>by <a href="mailto:giuseppe.pisano@unibo.it">Giuseppe Pisano</a>, <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/pco-woa-2021-distributedarg/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">We discuss the problem of cooperative argumentation in multi-agent systems, focusing on the computational model. An actor-based model is proposed as a first step towards cooperative argumentation in multi-agent systems to tackle distribution issues—illustrating a preliminary fully-distributed version of the argumentation process completely based on message passing.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/pco-woa-2021-distributedarg/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-2963/paper17.pdf">http://ceur-ws.org/Vol-2963/paper17.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/pco-woa-2021-distributedarg/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/pco-woa-2021-distributedarg/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">distributedarg-woa2021</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Pisano, Giuseppe and Calegari, Roberta and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2021 -- 22nd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Denti, Enrico and Omicini, Andrea and Sartor, Giovanni}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Argumentation, MAS, cooperative argumentation, distributed argumentation process}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">oct</span><span class="p">,</span>
<span class="na">note</span> <span class="p">=</span> <span class="s">{22nd Workshop ``From Objects to Agents'' (WOA 2021), Bologna, Italy, 1--3~}</span> <span class="p">#</span> <span class="nv">sep</span> <span class="p">#</span> <span class="s">{~2021. Proceedings}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">16</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{162--177}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Towards cooperative argumentation for {MAS}: An actor-based approach}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-2963/paper17.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">2963</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
On Explainable Negotiations via Argumentation
https://expectation.ehealth.hevs.ch/posts/publications/canc-bnaic-2021-explanable-negotiations/Amro NajjarDavide CalvaresiReyhan AydoğanVictor Hugo Contreras Ordonez2022-09-16T00:00:00+01:002022-09-16T16:24:57+02:00
<p>by Contreras, Victor and Aydoğan, Reyhan and Najjar, Amro and Calvaresi, Davide</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/canc-bnaic-2021-explanable-negotiations/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/canc-bnaic-2021-explanable-negotiations/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://publications.hevs.ch/index.php/publications/show/2883">http://publications.hevs.ch/index.php/publications/show/2883</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/canc-bnaic-2021-explanable-negotiations/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/canc-bnaic-2021-explanable-negotiations/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">canc-bnaic-2021-explanable-negotiations</span><span class="p">,</span>
<span class="na">address</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Contreras, Victor and Aydoğan, Reyhan and Najjar, Amro and Calvaresi, Davide}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Proceedings of BNAIC 2021}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">isbn-online</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{explainable negotiation}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{ACM}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{On Explainable Negotiations via Argumentation}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://publications.hevs.ch/index.php/publications/show/2883}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">00</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences
https://expectation.ehealth.hevs.ch/posts/publications/cdca+air-2022-global-taxonomy-xai/Davide Calvaresi2022-09-16T00:00:00+01:002022-09-16T16:24:57+02:00
<p>by Graziani, Mara and Dutkiewicz, Lidia and Calvaresi, Davide and Amorim, Jos{'e} Pereira and Yordanova, Katerina and Vered, Mor and Nair, Rahul and Abreu, Pedro Henriques and Blanke, Tobias and Pulignano, Valeria and Prior, John O. and Lauwaert, Lode and Reijers, Wessel and Depeursinge, Adrien and Andrearczyk, Vincent and Müller, Henning</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cdca+air-2022-global-taxonomy-xai/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are “weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cdca+air-2022-global-taxonomy-xai/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="https://link.springer.com/article/10.1007/s10462-022-10256-8">https://link.springer.com/article/10.1007/s10462-022-10256-8</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cdca+air-2022-global-taxonomy-xai/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cdca+air-2022-global-taxonomy-xai/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@Article</span><span class="p">{</span><span class="nl">cdca+air-2022-global-taxonomy-xai</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Graziani, Mara and Dutkiewicz, Lidia and Calvaresi, Davide and Amorim, Jos{\'e} Pereira and Yordanova, Katerina and Vered, Mor and Nair, Rahul and Abreu, Pedro Henriques and Blanke, Tobias and Pulignano, Valeria and Prior, John O. and Lauwaert, Lode and Reijers, Wessel and Depeursinge, Adrien and Andrearczyk, Vincent and Müller, Henning}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{Artificial Intelligence Review}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{1--32}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/s10462-022-10256-8}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://link.springer.com/article/10.1007/s10462-022-10256-8}</span><span class="p">,</span>
<span class="p">}</span>
</code></pre></div>
Human-Social Robots Interaction: the blurred line between necessary anthropomorphization and manipulation
https://expectation.ehealth.hevs.ch/posts/publications/cnc-expectation-2022-human-robots-interaction/Amro NajjarDavide Calvaresi2022-09-16T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by Rachele Carli and <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a> and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cnc-expectation-2022-human-robots-interaction/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cnc-expectation-2022-human-robots-interaction/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://publications.hevs.ch/index.php/publications/show/2932">http://publications.hevs.ch/index.php/publications/show/2932</a></li>
<li>DOI: <a href="https://doi.org/10.1145/3527188.3563941">https://doi.org/10.1145/3527188.3563941</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cnc-expectation-2022-human-robots-interaction/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/cnc-expectation-2022-human-robots-interaction/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">CarliNC22</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Rachele Carli and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Davide Calvaresi}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Christoph Bartneck and
</span><span class="s"> Takayuki Kanda and
</span><span class="s"> Mohammad Obaid and
</span><span class="s"> Wafa Johal}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Human-Social Robots Interaction: The Blurred Line between Necessary
</span><span class="s"> Anthropomorphization and Manipulation}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{International Conference on Human-Agent Interaction, {HAI} 2022, Christchurch,
</span><span class="s"> New Zealand, December 5-8, 2022}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{321--323}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{{ACM}}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1145/3527188.3563941}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1145/3527188.3563941}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Mon, 05 Dec 2022 13:35:52 +0100}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/hai/CarliNC22.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
The quest of parsimonious XAI: A human-agent architecture for explanation formulation
https://expectation.ehealth.hevs.ch/posts/publications/mtkn+ai-2022-quest-parsimonious-xai/Amro NajjarDavide CalvaresiIgor Tchappi2022-09-16T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by Yazan Mualla and <a href="mailto:igor.tchappi@uni.lu">Igor Tchappi</a> and Timotheus Kampik and <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a> and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a> and Abdeljalil Abbas-Turki and Stéphane Galland and Christophe Nicolle</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/mtkn+ai-2022-quest-parsimonious-xai/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">With the widespread use of Artificial Intelligence (AI), understanding the behavior of intelligent agents and robots is crucial to guarantee successful human-agent collaboration since it is not straightforward for humans to understand an agent’s state of mind. Recent empirical studies have confirmed that explaining a system’s behavior to human users fosters the latter’s acceptance of the system. However, providing overwhelming or unnecessary information may also confuse the users and cause failure. For these reasons, parsimony has been outlined as one of the key features allowing successful human-agent interaction with parsimonious explanation defined as the simplest explanation (i.e. least complex) that describes the situation adequately (i.e. descriptive adequacy). While parsimony is receiving growing attention in the literature, most of the works are carried out on the conceptual front. This paper proposes a mechanism for parsimonious eXplainable AI (XAI). In particular, it introduces the process of explanation formulation and proposes HAExA, a human-agent explainability architecture allowing to make it operational for remote robots. To provide parsimonious explanations, HAExA relies on both contrastive explanations and explanation filtering. To evaluate the proposed architecture, several research hypotheses are investigated in an empirical user study that relies on well-established XAI metrics to estimate how trustworthy and satisfactory the explanations provided by HAExA are. The results are analyzed using parametric and non-parametric statistical testing.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/mtkn+ai-2022-quest-parsimonious-xai/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="https://www.sciencedirect.com/science/article/pii/S0004370221001247">https://www.sciencedirect.com/science/article/pii/S0004370221001247</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/mtkn+ai-2022-quest-parsimonious-xai/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/mtkn+ai-2022-quest-parsimonious-xai/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@Article</span><span class="p">{</span><span class="nl">mtkn+ai-2022-quest-parsimonious-xai</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Mualla, Yazan and Tchappi, Igor and Kampik, Timotheus and Najjar, Amro and Calvaresi, Davide and Abbas-Turki, Abdeljalil and Galland, St{\'e}phane and Nicolle, Christophe}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{The quest of parsimonious XAI: A human-agent architecture for explanation formulation}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">jan</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{103573}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{302}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1016/j.artint.2021.103573}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Elsevier}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://www.sciencedirect.com/science/article/pii/S0004370221001247}</span><span class="p">,</span>
<span class="p">}</span>
</code></pre></div>
Explanation-Based Negotiation Protocol for Nutrition Virtual Coaching
https://expectation.ehealth.hevs.ch/posts/publications/buzcuvtnca22/Amro NajjarBerk BuzcuDavide CalvaresiIgor TchappiReyhan Aydoğan2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:berk.buzcu@ozu.edu.tr">Berk Buzcu</a>, Vanitha Varadhajaran, <a href="mailto:igor.tchappi@uni.lu">Igor Tchappi</a>, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a> and <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/buzcuvtnca22/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">People’s awareness about the importance of healthy lifestyles is rising. This opens new possibilities for personalized intelligent health and coaching applications. In particular, there is a need for more than simple recommendations and mechanistic interactions. Recent studies have identified nutrition virtual coaching systems (NVC) as a technological solution, possibly bridging technologies such as recommender, informative, persuasive, and argumentation systems. Enabling NVC to explain recommendations and discuss (argument) dietary solutions and alternative items or behaviors is crucial to improve the transparency of these applications and enhance user acceptability and retain their engagement. This study primarily focuses on virtual agents personalizing the generation of food recipes recommendation according to users’ allergies, eating habits, lifestyles, nutritional values, etc. Although the agent would nudge the user to consume healthier food, users may tend to object in favor of tastier food. To resolve this divergence, we propose a user-agent negotiation interacting over the revision of the recommendation (via feedback and explanations) or convincing (via explainable arguments) the user of its benefits and importance. Finally, the paper presents our initial findings on the acceptability and usability of such a system obtained via tests with real users. Our preliminary experimental results show that the majority of the participants appreciate the ability to express their feedback as well as receive explanations of the recommendations, while there is still room for improvement in the persuasiveness of the explanations.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/buzcuvtnca22/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-031-21203-1_2">https://doi.org/10.1007/978-3-031-21203-1_2</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/buzcuvtnca22/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/buzcuvtnca22/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">BuzcuVTNCA22</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Berk Buzcu and
</span><span class="s"> Vanitha Varadhajaran and
</span><span class="s"> Igor Tchappi and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Davide Calvaresi and
</span><span class="s"> Reyhan Aydogan}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Reyhan Aydogan and
</span><span class="s"> Natalia Criado and
</span><span class="s"> J{\'{e}}r{\^{o}}me Lang and
</span><span class="s"> V{\'{\i}}ctor S{\'{a}}nchez{-}Anguix and
</span><span class="s"> Marc Serramia}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Explanation-Based Negotiation Protocol for Nutrition Virtual Coaching}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{{PRIMA} 2022: Principles and Practice of Multi-Agent Systems - 24th
</span><span class="s"> International Conference, Valencia, Spain, November 16-18, 2022, Proceedings}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{13753}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{20--36}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/978-3-031-21203-1\_2}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-21203-1\_2}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Mon, 05 Dec 2022 13:35:34 +0100}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/prima/BuzcuVTNCA22.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
Integration of Local and Global Features Explanation with Global Rules Extraction and Generation Tools
https://expectation.ehealth.hevs.ch/posts/publications/contrerassc22/Davide CalvaresiMichael I. SchumacherVictor Hugo Contreras Ordonez2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:victor.contrerasordonez@hevs.ch">Contreras Ordoñez Victor Hugo</a>, <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a>, and <a href="mailto:michael.schumacher@hevs.ch">Michael I. Schumacher</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerassc22/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Widely used in a growing number of domains, Deep Learning predictors are achieving remarkable results. However, the lack of transparency (i.e., opacity) of their inner mechanisms has raised trust and employability concerns. Nevertheless, several approaches fostering models of interpretability and explainability have been developed in the last decade. This paper combines approaches for local feature explanation (i.e., Contextual Importance and Utility – CIU) and global feature explanation (i.e., Explainable Layers) with a rule extraction system, namely ECLAIRE. The proposed pipeline has been tested in four scenarios employing a breast cancer diagnosis dataset. The results show improvements such as the production of more human-interpretable rules and adherence of the produced rules with the original model.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerassc22/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-031-15565-9_2">https://doi.org/10.1007/978-3-031-15565-9_2</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerassc22/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerassc22/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">ContrerasSC22</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Victor Contreras and
</span><span class="s"> Michael Schumacher and
</span><span class="s"> Davide Calvaresi}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Davide Calvaresi and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Michael Winikoff and
</span><span class="s"> Kary Fr{\"{a}}mling}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Integration of Local and Global Features Explanation with Global Rules
</span><span class="s"> Extraction and Generation Tools}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent {AI} and Multi-Agent Systems - 4th International
</span><span class="s"> Workshop, {EXTRAAMAS} 2022, Virtual Event, May 9-10, 2022, Revised
</span><span class="s"> Selected Papers}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{13283}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{19--37}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/978-3-031-15565-9\_2}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-15565-9\_2}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Tue, 18 Oct 2022 22:16:54 +0200}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/atal/ContrerasSC22.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
Bidding Support by the Pocket Negotiator Improves Negotiation Outcomes
https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22a/Reyhan Aydoğan2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a>, and Catholijn M. Jonker</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22a/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">This paper presents the negotiation support mechanisms provided by the Pocket Negotiator (PN) and an elaborate empirical evaluation of the economic decision support (EDS) mechanisms during the bidding phase of negotiations as provided by the PN. Some of these support mechanisms are offered actively, some passively. With passive support we mean that the user only gets that support by clicking a button, whereas active support is provided without prompting. Our results show, that PN improves negotiation outcomes, counters cognitive depletion, and encourages exploration of potential outcomes. We found that the active mechanisms were used more effectively than the passive ones and, overall, the various mechanisms were not used optimally, which opens up new avenues for research. As expected, the participants with higher negotiation skills outperformed the other groups, but still they benefited from PN support. Our experimental results show that people with enough technical skills and with some basic negotiation knowledge will benefit most from PN support. Our results also show that the cognitive depletion effect is reduced by Pocket Negotiator support. The questionnaire taken after the experiment shows that overall the participants found Pocket Negotiator easy to interact with, that it made them negotiate more quickly and that it improves their outcome. Based on our findings, we recommend to 1) provide active support mechanisms (push) to nudge users to be more effective, and 2) provide support mechanisms that shield the user from mathematical complexities.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22a/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-981-99-0561-4_4">https://doi.org/10.1007/978-981-99-0561-4_4</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22a/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22a/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">AydoganJ22a</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Reyhan Aydogan and
</span><span class="s"> Catholijn M. Jonker}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Rafik Hadfi and
</span><span class="s"> Reyhan Aydogan and
</span><span class="s"> Takayuki Ito and
</span><span class="s"> Ryuta Arisaka}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Bidding Support by the Pocket Negotiator Improves Negotiation Outcomes}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Recent Advances in Agent-Based Negotiation: Applications and Competition
</span><span class="s"> Challenges, ACAN@IJCAI 2022, Vienna, Austria, July 24, 2022}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Studies in Computational Intelligence}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{1092}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{52--83}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/978-981-99-0561-4\_4}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-981-99-0561-4\_4}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Tue, 28 Mar 2023 19:49:35 +0200}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/acan/AydoganJ22a.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
A Survey of Decision Support Mechanisms for Negotiation
https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22b/Reyhan Aydoğan2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a>, and Catholijn M. Jonker</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22b/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">This paper introduces a dependency analysis and a categorization of conceptualized and existing economic decision support mechanisms for negotiation. The focus of our survey is on economic decision support mechanisms, although some behavioural support mechanisms were included, to recognize the important work in that area. We categorize support mechanisms from four different aspects: (i) economic versus behavioral decision support, (ii) analytical versus strategical support, (iii) active versus passive support and (iv) implicit versus explicit support. Our survey suggests that active mechanisms would be more effective than passive ones, and that implicit mechanisms can shield the user from mathematical complexities. Furthermore, we provide a list of existing economic support mechanisms.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22b/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-981-99-0561-4_3">https://doi.org/10.1007/978-981-99-0561-4_3</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22b/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/aydoganj22b/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">AydoganJ22b</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Reyhan Aydogan and
</span><span class="s"> Catholijn M. Jonker}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Rafik Hadfi and
</span><span class="s"> Reyhan Aydogan and
</span><span class="s"> Takayuki Ito and
</span><span class="s"> Ryuta Arisaka}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{A Survey of Decision Support Mechanisms for Negotiation}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Recent Advances in Agent-Based Negotiation: Applications and Competition
</span><span class="s"> Challenges, ACAN@IJCAI 2022, Vienna, Austria, July 24, 2022}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Studies in Computational Intelligence}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{1092}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{30--51}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/978-981-99-0561-4\_3}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-981-99-0561-4\_3}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Tue, 28 Mar 2023 19:49:35 +0200}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/acan/AydoganJ22.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
A DEXiRE for Extracting Propositional Rules from Neural Networks via Binarization
https://expectation.ehealth.hevs.ch/posts/publications/electronics11244171/Davide CalvaresiJean-Paul CalbimonteMichael I. SchumacherVictor Hugo Contreras Ordonez2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:victor.contrerasordonez@hevs.ch">Contreras Ordoñez Victor Hugo</a>, Niccolo Marini, Lora Fanda, Gaetano Manzo, Yazan Mualla, <a href="mailto:jean-paul.calbimonte@hevs.ch">Jean-Paul Calbimonte</a>, <a href="mailto:michael.schumacher@hevs.ch">Michael I. Schumacher</a>, and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/electronics11244171/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Background: Despite the advancement in eXplainable Artificial Intelligence, the explanations provided by model-agnostic predictors still call for improvements (i.e., lack of accurate descriptions of predictors’ behaviors). Contribution: We present a tool for Deep Explanations and Rule Extraction (DEXiRE) to approximate rules for Deep Learning models with any number of hidden layers. Methodology: DEXiRE proposes the binarization of neural networks to induce Boolean functions in the hidden layers, generating as many intermediate rule sets. A rule set is inducted between the first hidden layer and the input layer. Finally, the complete rule set is obtained using inverse substitution on intermediate rule sets and first-layer rules. Statistical tests and satisfiability algorithms reduce the final rule set’s size and complexity (filtering redundant, inconsistent, and non-frequent rules). DEXiRE has been tested in binary and multiclass classifications with six datasets having different structures and models. Results: The performance is consistent (in terms of accuracy, fidelity, and rule length) with respect to the state-of-the-art rule extractors (i.e., ECLAIRE). Moreover, compared with ECLAIRE, DEXiRE has generated shorter rules (i.e., up to 74% fewer terms) and has shortened the execution time (improving up to 197% in the best-case scenario). Conclusions: DEXiRE can be applied for binary and multiclass classification of deep learning predictors with any number of hidden layers. Moreover, DEXiRE can identify the activation pattern per class and use it to reduce the search space for rule extractors (pruning irrelevant/redundant neurons)—shorter rules and execution times with respect to ECLAIRE.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/electronics11244171/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.3390/electronics11244171">https://doi.org/10.3390/electronics11244171</a></li>
<li>URL: <a href="https://www.mdpi.com/2079-9292/11/24/4171">https://www.mdpi.com/2079-9292/11/24/4171</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/electronics11244171/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/electronics11244171/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex">
<span class="nc">@Article</span><span class="p">{</span><span class="nl">electronics11244171</span><span class="p">,</span>
<span class="na">AUTHOR</span> <span class="p">=</span> <span class="s">{Contreras, Victor and Marini, Niccolo and Fanda, Lora and Manzo, Gaetano and Mualla, Yazan and Calbimonte, Jean-Paul and Schumacher, Michael and Calvaresi, Davide}</span><span class="p">,</span>
<span class="na">TITLE</span> <span class="p">=</span> <span class="s">{A DEXiRE for Extracting Propositional Rules from Neural Networks via Binarization}</span><span class="p">,</span>
<span class="na">JOURNAL</span> <span class="p">=</span> <span class="s">{Electronics}</span><span class="p">,</span>
<span class="na">VOLUME</span> <span class="p">=</span> <span class="s">{11}</span><span class="p">,</span>
<span class="na">YEAR</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">NUMBER</span> <span class="p">=</span> <span class="s">{24}</span><span class="p">,</span>
<span class="na">ARTICLE-NUMBER</span> <span class="p">=</span> <span class="s">{4171}</span><span class="p">,</span>
<span class="na">URL</span> <span class="p">=</span> <span class="s">{https://www.mdpi.com/2079-9292/11/24/4171}</span><span class="p">,</span>
<span class="na">ISSN</span> <span class="p">=</span> <span class="s">{2079-9292}</span><span class="p">,</span>
<span class="na">DOI</span> <span class="p">=</span> <span class="s">{10.3390/electronics11244171}</span>
<span class="p">}</span>
</code></pre></div>
Ethical and legal considerations for nutrition virtual coaches
https://expectation.ehealth.hevs.ch/posts/publications/calvaresicpcl+2022/Amro NajjarDavide CalvaresiJean-Paul CalbimonteMichael I. SchumacherVictor Hugo Contreras Ordonez2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a>, Rachele Carli, Jean-Gabriel Piguet, <a href="mailto:victor.contrerasordonez@hevs.ch">Contreras Ordoñez Victor Hugo</a>, Gloria Luzzani, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, <a href="mailto:jean-paul.calbimonte@hevs.ch">Jean-Paul Calbimonte</a>, and <a href="mailto:michael.schumacher@hevs.ch">Michael I. Schumacher</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/calvaresicpcl+2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Choices and preferences of individuals are nowadays increasingly influenced by countless inputs and recommendations provided by artificial intelligence-based systems. The accuracy of recommender systems (RS) has achieved remarkable results in several domains, from infotainment to marketing and lifestyle. However, in sensitive use-cases, such as nutrition, there is a need for more complex dynamics and responsibilities beyond conventional RS frameworks. On one hand, virtual coaching systems (VCS) are intended to support and educate the users about food, integrating additional dimensions w.r.t. the conventional RS (i.e., leveraging persuasion techniques, argumentation, informative systems, and recommendation paradigms) and show promising results. On the other hand, as of today, VCS raise unexplored ethical and legal concerns. This paper discusses the need for a clear understanding of the ethical/legal-technological entanglements, formalizing 21 ethical and ten legal challenges and the related mitigation strategies. Moreover, it elaborates on nutrition sustainability as a further nutrition virtual coaches dimension for a better society.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/calvaresicpcl+2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/s43681-022-00237-6">https://doi.org/10.1007/s43681-022-00237-6</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/calvaresicpcl+2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/calvaresicpcl+2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">CalvaresiCPCL+2022</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/s43681-022-00237-6}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/s43681-022-00237-6}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">nov</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Science and Business Media {LLC}}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Davide Calvaresi and Rachele Carli and Jean-Gabriel Piguet and Victor H. Contreras and Gloria Luzzani and Amro Najjar and Jean-Paul Calbimonte and Michael Schumacher}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Ethical and legal considerations for nutrition virtual coaches}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{{AI} and Ethics}</span>
<span class="p">}</span>
</code></pre></div>
Risk and Exposure of XAI in Persuasion and Argumentation: The case of Manipulation
https://expectation.ehealth.hevs.ch/posts/publications/carlinc22/Amro NajjarDavide Calvaresi2023-04-29T00:00:00+01:002023-04-29T19:09:07+02:00
<p>by Rachele Carli, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlinc22/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify"><p>In the last decades, Artificial intelligence (AI) systems have been increasingly adopted in assistive (possibly collaborative) decision-making tools. In particular, AI-based persuasive technologies are designed to steer/influence users’ behaviour, habits, and choices to facilitate the achievement of their own - predetermined - goals. Nowadays, the inputs received by the assistive systems leverage heavily AI data-driven approaches. Thus, it is imperative to have transparent and understandable (to the user) both the process leading to the recommendations and the recommendations. The Explainable AI (XAI) community has progressively contributed to “opening the black box”, ensuring the interaction’s effectiveness, and pursuing the safety of the individuals involved. However, principles and methods ensuring the efficacy and information retain on the human have not been introduced yet. The risk is to underestimate the context dependency and subjectivity of the explanations’ understanding, interpretation, and relevance. Moreover, even a plausible (and possibly expected) explanation can lead to an imprecise or incorrect outcome or its understanding. This can lead to unbalanced and unfair circumstances, such as giving a financial advantage to the system owner/provider and the detriment of the user.</p>
<p>This paper highlights that the sole explanations - especially in the context of persuasive technologies - are not self-sufficient to protect users’ psychological and physical integrity. Conversely, explanations could be misused, becoming themselves a tool of manipulation. Therefore, we suggest characteristics safeguarding the explanation from being manipulative and legal principles to be used as criteria for evaluating the operation of XAI systems, both from an ex-ante and ex-post perspective.</p>
</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlinc22/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-031-15565-9_13">https://doi.org/10.1007/978-3-031-15565-9_13</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlinc22/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlinc22/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">CarliNC22</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Rachele Carli and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Davide Calvaresi}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Davide Calvaresi and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Michael Winikoff and
</span><span class="s"> Kary Fr{\"{a}}mling}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Risk and Exposure of {XAI} in Persuasion and Argumentation: The case
</span><span class="s"> of Manipulation}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent {AI} and Multi-Agent Systems - 4th International
</span><span class="s"> Workshop, {EXTRAAMAS} 2022, Virtual Event, May 9-10, 2022, Revised
</span><span class="s"> Selected Papers}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{13283}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{204--220}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2022}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/978-3-031-15565-9\_13}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-15565-9\_13}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Tue, 18 Oct 2022 22:16:54 +0200}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/conf/atal/CarliNC22.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
Towards cooperative argumentation for MAS: An actor-based approach
https://expectation.ehealth.hevs.ch/posts/publications/distributedarg-woa2021/Andrea OmiciniRoberta Calegari2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by Giuseppe Pisano, <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/distributedarg-woa2021/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">We discuss the problem of cooperative argumentation in multi-agent systems, focusing on the computational model. An actor-based model is proposed as a first step towards cooperative argumentation in multi-agent systems to tackle distribution issues—illustrating a preliminary fully-distributed version of the argumentation process completely based on message passing.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/distributedarg-woa2021/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-2963/paper17.pdf">http://ceur-ws.org/Vol-2963/paper17.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/distributedarg-woa2021/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/distributedarg-woa2021/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">distributedarg-woa2021</span><span class="p">,</span>
<span class="na">articleno</span> <span class="p">=</span> <span class="m">12</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Pisano, Giuseppe and Calegari, Roberta and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2021 -- 22nd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/woa/PisanoCO21}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Denti, Enrico and Omicini, Andrea and Sartor, Giovanni}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/834366}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Argumentation, MAS, cooperative argumentation, distributed argumentation process}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">oct</span><span class="p">,</span>
<span class="na">note</span> <span class="p">=</span> <span class="s">{22nd Workshop ``From Objects to Agents'' (WOA 2021), Bologna, Italy, 1--3~}</span> <span class="p">#</span> <span class="nv">sep</span> <span class="p">#</span> <span class="s">{~2021. Proceedings}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">16</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{162--177}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{13615595110063768054}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85116856131}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Towards cooperative argumentation for {MAS}: An actor-based approach}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-2963/paper17.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">2963</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2021</span>
<span class="p">}</span>
</code></pre></div>
Hypercube-Based Methods for Symbolic Knowledge Extraction: Towards a Unified Model
https://expectation.ehealth.hevs.ch/posts/publications/hypercube-woa2022/Andrea OmiciniFederico SabbatiniGiovanni CiattoRoberta Calegari2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:f.sabbatini@unibo.it">Federico Sabbatini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:roberta.calegari@unibo.it">Roberta Calegari</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hypercube-woa2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Symbolic knowledge-extraction (SKE) algorithms proposed by the XAI community to obtain human-intelligible explanations for opaque machine learning predictors are currently being studied and developed with growing interest, also in order to achieve believability in interactions. However, choosing the most adequate extraction procedure amongst the many existing in the literature is becoming more and more challenging, as the amount of available methods increases. In fact, most of the proposed algorithms come with constraints over their applicability.
In this paper we focus upon a quite general class of SKE techniques, namely hypercube-based methods. Despite being commonly considered regression-specific, we discuss why hypercube-based SKE methods are flexible enough to deal with classification problems as well. More generally, we propose a common generalised model for hypercube-based methods, and we show how they can be exploited to perform SKE on datasets, predictors, or learning tasks of any sort.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hypercube-woa2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-3261/paper4.pdf">http://ceur-ws.org/Vol-3261/paper4.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hypercube-woa2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hypercube-woa2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">hypercube-woa2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Sabbatini, Federico and Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2022 -- 23rd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/woa/SabbatiniCCO22}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Ferrando, Angelo and Mascardi, Viviana}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/899358}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Explainable AI; Knowledge extraction; Interpretable prediction; PSyKE}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">nov</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">13</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{48--60}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{8614662013642803891}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AIxIA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Hypercube-Based Methods for Symbolic Knowledge Extraction: Towards a Unified Model}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper4.pdf}</span><span class="p">,</span>
<span class="na">urlopenaccess</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper4.pdf}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper4.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">3261</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors
https://expectation.ehealth.hevs.ch/posts/publications/psyki-extraamas2022/Andrea OmiciniGiovanni CiattoMatteo Magnini2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/psyki-extraamas2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">A long-standing ambition in artificial intelligence is to integrate predictors' inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from prior symbolic knowledge). Many algorithms methods in the literature support injection of prior symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, a unified, coherent software framework supporting them as well as their interchange, comparison and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/psyki-extraamas2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-031-15565-9_6">https://doi.org/10.1007/978-3-031-15565-9_6</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/psyki-extraamas2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/psyki-extraamas2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">psyki-extraamas2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems}</span><span class="p">,</span>
<span class="na">chapter</span> <span class="p">=</span> <span class="m">6</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/atal/MagniniCO22}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-15565-9_6}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Främling, Kary}</span><span class="p">,</span>
<span class="na">eisbn</span> <span class="p">=</span> <span class="s">{978-3-031-15565-9}</span><span class="p">,</span>
<span class="na">eissn</span> <span class="p">=</span> <span class="s">{1611-3349}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/899511}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-031-15564-2}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Symbolic Knowledge Injection, Explainable AI, XAI, Neural Networks, PSyKI}</span><span class="p">,</span>
<span class="na">note</span> <span class="p">=</span> <span class="s">{4th International Workshop, EXTRAAMAS 2022, Virtual Event, May 9--10, 2022, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{90--108}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{7587528289517313138}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85138317005}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{On the Design of {PSyKI}: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://link.springer.com/chapter/10.1007/978-3-031-15565-9_6}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{https://link.springer.com/content/pdf/10.1007/978-3-031-15565-9_6.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">13283</span><span class="p">,</span>
<span class="na">wos</span> <span class="p">=</span> <span class="s">{000870042100006}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
KINS: Knowledge Injection via Network Structuring
https://expectation.ehealth.hevs.ch/posts/publications/kins-cilc2022/Andrea OmiciniGiovanni CiattoMatteo Magnini2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kins-cilc2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">We propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called KINS (Knowledge Injection via Network Structuring). The idea behind our method is to extend NN internal structure with ad-hoc layers built out the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported to demonstrate the potential of KINS.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kins-cilc2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="http://ceur-ws.org/Vol-3204/paper_25.pdf">http://ceur-ws.org/Vol-3204/paper_25.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kins-cilc2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kins-cilc2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">kins-cilc2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{CILC 2022 -- Italian Conference on Computational Logic}</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/cilc/MagniniCO22}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/899494}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{neural network; explainable AI; symbolic knowledge injection; KINS; PSyKI}</span><span class="p">,</span>
<span class="na">location</span> <span class="p">=</span> <span class="s">{Bologna, Italy}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">14</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{254--267}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{CEUR-WS}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{10469078385425944401}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85138240764}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AI*IA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{{KINS}: Knowledge Injection via Network Structuring}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_25.pdf}</span><span class="p">,</span>
<span class="na">urlopenaccess</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_25.pdf}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3204/paper_25.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">3204</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
Semantic Web-Based Interoperability for Intelligent Agents with PSyKE
https://expectation.ehealth.hevs.ch/posts/publications/swpsyke-extraamas2022/Andrea OmiciniFederico SabbatiniGiovanni Ciatto2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:f.sabbatini@unibo.it">Federico Sabbatini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/swpsyke-extraamas2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify"><p>Modern distributed systems require communicating agents to agree on a shared, formal semantics for the data they exchange and operate upon. The Semantic Web offers tools to encode semantics in the form of ontologies, where data is represented in the form knowledge graphs (KG). Applying such tools to intelligent agents equipped with machine learning (ML) capabilities is of particular interest, as it may enable a higher degree of interoperability among heterogeneous agents. Indeed, inputs and outputs of ML models can be formalised through ontologies, while the data they operate upon can be represented as KG.</p>
<p>In this paper we explore the combination of Semantic Web tools with knowledge extraction-that is, a research line aimed at extracting intelligible rules mimicking the behaviour of ML predictors, with the purpose of explaining their behaviour. Along this line, we study whether and to what extent ontologies and KG can be exploited as both the source and the outcome of a rule extraction procedure. In other words, we investigate the extraction of semantic rules out of sub-symbolic predictors trained upon data as KG-possibly adhering to some ontology. In doing so, we extend our PSyKE framework for rule extraction with Semantic Web support. In practice, we make PSyKE able to (i) train ML predictors out of OWL ontologies and RDF knowledge graphs, and (ii) extract semantic knowledge out of them, in the form of SWRL rules. A discussion among the major benefits and issues of our approach is provided, along with a description of the overall workflow.</p>
</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/swpsyke-extraamas2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/978-3-031-15565-9_8">https://doi.org/10.1007/978-3-031-15565-9_8</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/swpsyke-extraamas2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/swpsyke-extraamas2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">swpsyke-extraamas2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Sabbatini, Federico and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent AI and Multi-Agent Systems}</span><span class="p">,</span>
<span class="na">chapter</span> <span class="p">=</span> <span class="m">8</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/atal/SabbatiniCO22}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-15565-9_8}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Winikoff, Michael and Främling, Kary}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/899474}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-031-15564-2}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Symbolic Knowledge Injection, Explainable AI, XAI, Neural Networks, PSyKI}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">19</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{124--142}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{11339767386934277898}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85140488560}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subtitle</span> <span class="p">=</span> <span class="s">{4th International Workshop, EXTRAAMAS 2022, Virtual Event, May 9–10, 2022, Revised Selected Papers}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Semantic Web-Based Interoperability for Intelligent Agents with {PSyKE}}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-031-15565-9_8}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{https://link.springer.com/content/pdf/10.1007/978-3-031-15565-9_8.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">13283</span><span class="p">,</span>
<span class="na">wos</span> <span class="p">=</span> <span class="s">{000870042100008}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
A view to a KILL: Knowledge Injection via Lambda Layer
https://expectation.ehealth.hevs.ch/posts/publications/kill-woa2022/Andrea OmiciniGiovanni CiattoMatteo Magnini2023-04-29T00:00:00+01:002023-04-29T19:43:53+02:00
<p>by <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kill-woa2022/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">We propose KILL (Knowledge Injection via Lambda Layer) as a novel method for the injection of symbolic knowledge into neural networks (NN) allowing data scientists to control what the network should (not) learn. Unlike other similar approaches, our method does not (i) require ground input formulae, (ii) impose any constraint on the NN undergoing injection, (iii) affect the loss function of the NN. Instead, it acts directly at the backpropagation level, by increasing penalty whenever the NN output is violating the injected knowledge. Experiments are reported to demonstrate the potential (and limits) of our approach.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kill-woa2022/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="http://ceur-ws.org/Vol-3261/paper5.pdf">http://ceur-ws.org/Vol-3261/paper5.pdf</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kill-woa2022/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kill-woa2022/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">kill-woa2022</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{WOA 2022 -- 23rd Workshop ``From Objects to Agents''}</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/woa/MagniniCO22}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Ferrando, Angelo and Mascardi, Viviana}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/899373}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{1613-0073}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{symbolic knowledge injection; AI; ML; neural networks; KILL; PSyKI}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">nov</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">16</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{61--76}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Sun SITE Central Europe, RWTH Aachen University}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{514437633827732665}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85142481549}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{CEUR Workshop Proceedings}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{AIxIA Series}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{A view to a {KILL}: Knowledge Injection via Lambda Layer}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper5.pdf}</span><span class="p">,</span>
<span class="na">urlopenaccess</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper5.pdf}</span><span class="p">,</span>
<span class="na">urlpdf</span> <span class="p">=</span> <span class="s">{http://ceur-ws.org/Vol-3261/paper5.pdf}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">3261</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2022</span>
<span class="p">}</span>
</code></pre></div>
Symbolic Knowledge Extraction for Explainable Nutritional Recommenders
https://expectation.ehealth.hevs.ch/posts/publications/skerecommender-cmbp2023/Andrea OmiciniFurkan CanturkGiovanni CiattoMatteo MagniniReyhan Aydoğan2023-04-29T00:00:00+01:002023-04-29T20:10:50+02:00
<p>by <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:furkan.canturk@ozu.edu.tr">Furkan Canturk</a>, <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/skerecommender-cmbp2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify"><p>Background and objective This paper focuses on nutritional recommendation systems (RS), i.e. AI-powered automatic systems providing users with suggestions about what to eat to pursue their weight/body shape goals. A trade-off among (potentially) conflictual requirements must be taken into account when designing these kinds of systems, there including: (i) adherence to experts’ prescriptions, (ii) adherence to users’ tastes and preferences, (iii) explainability of the whole recommendation process. Accordingly, in this paper we propose a novel approach to the engineering of nutritional RS, combining machine learning and symbolic knowledge extraction to profile users—hence harmonising the aforementioned requirements.</p>
<p>Methods Our contribution focuses on the data processing workflow. Stemming from neural networks (NN) trained to predict user preferences, we use CART Breiman et al.(1984) to extract symbolic rules in Prolog Körner et al.(2022) form, and we combine them with expert prescriptions brought in similar form. We can then query the resulting symbolic knowledge base via logic solvers, to draw explainable recommendations.</p>
<p>Results Experiments are performed involving a publicly available dataset of 45,723 recipes, plus 12 synthetic datasets about as many imaginary users, and 6 experts’ prescriptions. Fully-connected 4-layered NN are trained on those datasets, reaching ∼86% test-set accuracy, on average. Extracted rules, in turn, have ∼80% fidelity w.r.t. those NN. The resulting recommendation system has a test-set precision of ∼74%. The symbolic approach makes it possible to devise how the system draws recommendations.</p>
<p>Conclusions Thanks to our approach, intelligent agents may learn users’ preferences from data, convert them into symbolic form, and extend them with experts’ goal-directed prescriptions. The resulting recommendations are then simultaneously acceptable for the end user and adequate under a nutritional perspective, while the whole process of recommendation generation is made explainable.</p>
</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/skerecommender-cmbp2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1016/j.cmpb.2023.107536">https://doi.org/10.1016/j.cmpb.2023.107536</a></li>
<li>URL: <a href="https://www.sciencedirect.com/science/article/pii/S0169260723002018">https://www.sciencedirect.com/science/article/pii/S0169260723002018</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/skerecommender-cmbp2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/skerecommender-cmbp2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">skerecommender-cmbp2023</span><span class="p">,</span>
<span class="na">articleno</span> <span class="p">=</span> <span class="m">107536</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Magnini, Matteo and Ciatto, Giovanni and Cantürk, Furkan and Aydoǧan, Reyhan and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1016/j.cmpb.2023.107536}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/923772}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0169-2607}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{Computer Methods and Programs in Biomedicine}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{explainable artificial intelligence, symbolic knowledge extraction, recommendation systems, nutrition, neural networks}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">jun</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">32</span><span class="p">,</span>
<span class="na">pubmed</span> <span class="p">=</span> <span class="s">{37060685}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{14455392383017605572}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85152230884}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Symbolic Knowledge Extraction for Explainable Nutritional Recommenders}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://www.sciencedirect.com/science/article/pii/S0169260723002018}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">235</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2023</span>
<span class="p">}</span>
</code></pre></div>
Reinterpreting Vulnerability to Tackle Deception in Principles-Based XAI for Human-Computer Interaction
https://expectation.ehealth.hevs.ch/posts/publications/carlid2023/Davide Calvaresi2023-04-29T00:00:00+01:002023-04-29T20:10:50+02:00
<p>by Rachele Carli, and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlid2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlid2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p>TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlid2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/carlid2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="c">TBD</span>
</code></pre></div>
A General-Purpose Protocol for Multi-Agent based Explanations
https://expectation.ehealth.hevs.ch/posts/publications/ciattombao2023/Andrea OmiciniBerk BuzcuGiovanni CiattoMatteo MagniniReyhan Aydoğan2024-03-07T00:00:00+01:002024-03-07T14:36:16+01:00
<p>by <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, <a href="mailto:berk.buzcu@ozu.edu.tr">Berk Buzcu</a>, <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ciattombao2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Building on prior works on explanation negotiation protocols, this paper proposes a general-purpose protocol for multi-agent systems where recommender agents may need to provide explanations for their recommendations. The protocol specifies the roles and responsibilities of the explainee and the explainer agent and the types of information that should be exchanged between them to ensure a clear and effective explanation. However, it does not prescribe any particular sort of recommendation or explanation, hence remaining agnostic w.r.t. such notions. Novelty lays in the extended support for both ordinary and contrastive explanations, as well as for the situation where no explanation is needed as none is requested by the explainee. Accordingly, we formally present and analyse the protocol, motivating its design and discussing its generality. We also discuss the reification of the protocol into a re-usable software library, namely PyXMas, which is meant to support developers willing to build explainable MAS leveraging our protocol. Finally, we discuss how custom notions of recommendation and explanation can be easily plugged into PyXMas.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ciattombao2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="http://dx.doi.org/10.1007/978-3-031-40878-6_3">http://dx.doi.org/10.1007/978-3-031-40878-6_3</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ciattombao2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/ciattombao2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@incollection</span><span class="p">{</span><span class="nl">explanationprotocol-extraamas2023</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Ciatto, Giovanni and Magnini, Matteo and Bezcu, Berk and Aydoǧan, Reyhan and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent {AI} and Multi-Agent Systems}</span><span class="p">,</span>
<span class="na">chapter</span> <span class="p">=</span> <span class="m">3</span><span class="p">,</span>
<span class="na">dblp</span> <span class="p">=</span> <span class="s">{conf/extraamas/CiattoMBAO23}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-40878-6_3}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Calvaresi, Davide and Najjar, Amro and Omicini, Andrea and Aydoǧan, Reyhan and Carli, Rachele and Ciatto, Giovanni and Mualla, Yazan and Främling, Kary}</span><span class="p">,</span>
<span class="na">iris</span> <span class="p">=</span> <span class="s">{11585/940656}</span><span class="p">,</span>
<span class="na">isbn</span> <span class="p">=</span> <span class="s">{978-3-031-40878-6}</span><span class="p">,</span>
<span class="na">issn</span> <span class="p">=</span> <span class="s">{0302-9743}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{XAI, Recommender Systems, Multi-agent systems, Explanation protocols}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">sep</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">22</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{38--58}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{5371175139312621961}</span><span class="p">,</span>
<span class="na">scopus</span> <span class="p">=</span> <span class="s">{2-s2.0-85172214167}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">subseries</span> <span class="p">=</span> <span class="s">{Lecture Notes in Artificial Intelligence}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{A General-Purpose Protocol for Multi-Agent based Explanations}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://link.springer.com/10.1007/978-3-031-40878-6_3}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="m">14127</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2023</span>
<span class="p">}</span>
</code></pre></div>
Explanation Generation via Decompositional Rules Extraction for Head and Neck Cancer Classification
https://expectation.ehealth.hevs.ch/posts/publications/contrerasbmsac2023/Davide Calvaresi2023-04-29T00:00:00+01:002023-04-29T20:10:50+02:00
<p>by <a href="mailto:victor.contrerasordonez@hevs.ch">Contreras Ordoñez Victor Hugo</a>, Andrea Bagante, Niccolò Marini, <a href="mailto:michael.schumacher@hevs.ch">Michael I. Schumacher</a>, Vincent Andrearczyk and <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerasbmsac2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerasbmsac2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p>TBD</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerasbmsac2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/contrerasbmsac2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="c">TBD</span>
</code></pre></div>
Metrics for Evaluating Explainable Recommender Systems
https://expectation.ehealth.hevs.ch/posts/publications/hulstintna2023/Amro NajjarIgor TchappiJoris HulstijnReyhan Aydoğan2023-04-29T00:00:00+01:002023-11-06T15:44:55+01:00
<p>by <a href="mailto:joris.hulstijn@uni.lu">Joris Hulstijn</a>, <a href="mailto:igor.tchappi@uni.lu">Igor Tchappi</a>, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, and <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstintna2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Recommender systems aim to support their users by reducing information overload so that they can make better decisions. Recommender systems must be transparent, so users can form mental models about the system’s goals, internal state, and capabilities, that are in line with their actual design. Explanations and transparent behaviour of the system should inspire trust and, ultimately, lead to more persuasive recommendations. Here, explanations convey reasons why a recommendation is given or how the system forms its recommendations. This paper focuses on the question how such claims about effectiveness of explanations can be evaluated. Accordingly, we investigate various models that are used to assess the effects of explanations and recommendations. We discuss objective and subjective measurement and argue that both are needed. We define a set of metrics for measuring the effectiveness of explanations and recommendations. The feasibility of using these metrics is discussed in the context of a specific explainable recommender system in the food and health domain.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstintna2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="https://link.springer.com/chapter/10.1007/978-3-031-40878-6_12">https://link.springer.com/chapter/10.1007/978-3-031-40878-6_12</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstintna2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstintna2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">HulstijnTNA23</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Joris Hulstijn and
</span><span class="s"> Igor Tchappi and
</span><span class="s"> Amro Najjar and
</span><span class="s"> Reyhan Aydogan}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Davide Calvaresi et al}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Metrics for Evaluating Explainable Recommender Systems}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Explainable and Transparent {AI} and Multi-Agent Systems - 5th International
</span><span class="s"> Workshop, (EXTRAAMAS 2023), London, UK.
</span><span class="s"> Papers}</span><span class="p">,</span>
<span class="na">series</span> <span class="p">=</span> <span class="s">{Lecture Notes in Computer Science}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{14127}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{212--230}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2023}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://link.springer.com/chapter/10.1007/978-3-031-40878-6_12}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/978-3-031-40878-6_12}</span>
<span class="p">}</span>
</code></pre></div>
Computational Accountability
https://expectation.ehealth.hevs.ch/posts/publications/hulstijn23/Joris Hulstijn2023-11-06T00:00:00+01:002023-11-06T15:44:55+01:00
<p>by <a href="mailto:joris.hulstijn@uni.lu">Joris Hulstijn</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstijn23/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Automated decision making systems take decisions that matter. Some human or legal person remains responsible. Looking back, that person is accountable for the decisions made by the system, and may even be liable in case of damages. That puts constraints on the way in which decision making systems are designed, and how they are deployed in organizations. In this paper, we analyze computational accountability in three steps. First, being accountable is analyzed as a relationship between an actor deploying the system and a critical forum of subjects, users, experts and developers. Second, we discuss system design. In principle, evidence must be collected about the decision rule and the case data that were applied. However, many AI algorithms are not interpretable for humans. Alternatively, internal controls must ensure that a system uses valid algorithms and reliable data sets for training, which are appropriate for the application domain. Third, we discuss the governance model: roles, responsibilities, procedures and infrastructure, to ensure effective operation of these controls. The paper ends with a case study in the IT audit domain, to illustrate practical feasibility.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstijn23/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="https://dl.acm.org/doi/10.1145/3594536.3595122">https://dl.acm.org/doi/10.1145/3594536.3595122</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstijn23/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/hulstijn23/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@inproceedings</span><span class="p">{</span><span class="nl">Hulstijn23</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Joris Hulstijn}</span><span class="p">,</span>
<span class="na">editor</span> <span class="p">=</span> <span class="s">{Matthias Grabmair and
</span><span class="s"> Francisco Andrade and
</span><span class="s"> Paulo Novais}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Computational Accountability}</span><span class="p">,</span>
<span class="na">booktitle</span> <span class="p">=</span> <span class="s">{Proceedings of the Nineteenth International Conference on Artificial
</span><span class="s"> Intelligence and Law, {ICAIL} 2023, Braga, Portugal, June 19-23, 2023}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{121--130}</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{{ACM}}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2023}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://dl.acm.org/doi/10.1145/3594536.3595122}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1145/3594536.3595122}</span>
<span class="p">}</span>
</code></pre></div>
Conflict-based negotiation strategy for human-agent negotiation
https://expectation.ehealth.hevs.ch/posts/publications/keskinba23/Berk BuzcuReyhan Aydoğan2023-11-06T00:00:00+01:002023-11-06T15:56:55+01:00
<p>by Mehmet Onur Keskin, <a href="mailto:berk.buzcu@ozu.edu.tr">Berk Buzcu</a>, and <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/keskinba23/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Day by day, human-agent negotiation becomes more and more vital to reach a socially beneficial agreement when stakeholders need to make a joint decision together. Developing agents who understand not only human preferences but also attitudes is a significant prerequisite for this kind of interaction. Studies on opponent modeling are predominantly based on automated negotiation and may yield good predictions after exchanging hundreds of offers. However, this is not the case in human-agent negotiation in which the total number of rounds does not usually exceed tens. For this reason, an opponent model technique is needed to extract the maximum information gained with limited interaction. This study presents a conflict-based opponent modeling technique and compares its prediction performance with the well-known approaches in human-agent and automated negotiation experimental settings. According to the results of human-agent studies, the proposed model outpr erforms them despite the diversity of participants’ negotiation behaviors. Besides, the conflict-based opponent model estimates the entire bid space much more successfully than its competitors in automated negotiation sessions when a small portion of the outcome space was explored. This study may contribute to developing agents that can perceive their human counterparts’ preferences and behaviors more accurately, acting cooperatively and reaching an admissible settlement for joint interests</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/keskinba23/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>URL: <a href="https://link.springer.com/article/10.1007/s10489-023-05001-9">https://link.springer.com/article/10.1007/s10489-023-05001-9</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/keskinba23/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/keskinba23/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">Keskin2023</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/s10489-023-05001-9}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://link.springer.com/article/10.1007/s10489-023-05001-9}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2023}</span><span class="p">,</span>
<span class="na">month</span> <span class="p">=</span> <span class="nv">nov</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{Springer Science and Business Media {LLC}}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Mehmet Onur Keskin and Berk Buzcu and Reyhan Aydo{\u{g}}an}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Conflict-based negotiation strategy for human-agent negotiation}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{Applied Intelligence}</span>
<span class="p">}</span>
</code></pre></div>
A Survey of Decision Support Mechanisms for Negotiation
https://expectation.ehealth.hevs.ch/posts/publications/bttnhca-jaamas-2024/Amro NajjarBerk BuzcuDavide CalvaresiIgor TchappiJoris HulstijnMelissa TessaReyhan Aydoğan2024-03-07T00:00:00+01:002024-03-07T14:28:14+01:00
<p>by <a href="mailto:berk.buzcu@ozu.edu.tr">Berk Buzcu</a>, <a href="mailto:im_tessa@esi.dz">Melissa Tessa</a>, <a href="mailto:igor.tchappi@uni.lu">Igor Tchappi</a>, <a href="mailto:amro.najjar@uni.lu">Amro Najjar</a>, <a href="mailto:joris.hulstijn@uni.lu">Joris Hulstijn</a>, <a href="mailto:davide.calvaresi@hevs.ch">Davide Calvaresi</a>, and <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/bttnhca-jaamas-2024/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">The awareness about healthy lifestyles is increasing, opening to personalized intelligent health coaching applications. A demand for more than mere suggestions and mechanistic interactions has driven attention to nutrition virtual coaching systems (NVC) as a bridge between human–machine interaction and recommender, informative, persuasive, and argumentation systems. NVC can rely on data-driven opaque mechanisms. Therefore, it is crucial to enable NVC to explain their doing (i.e., engaging the user in discussions (via arguments) about dietary solutions/alternatives). By doing so, transparency, user acceptance, and engagement are expected to be boosted. This study focuses on NVC agents generating personalized food recommendations based on user-specific factors such as allergies, eating habits, lifestyles, and ingredient preferences. In particular, we propose a user-agent negotiation process entailing run-time feedback mechanisms to react to both recommendations and related explanations. Lastly, the study presents the findings obtained by the experiments conducted with multi-background participants to evaluate the acceptability and effectiveness of the proposed system. The results indicate that most participants value the opportunity to provide feedback and receive explanations for recommendations. Additionally, the users are fond of receiving information tailored to their needs. Furthermore, our interactive recommendation system performed better than the corresponding traditional recommendation system in terms of effectiveness regarding the number of agreements and rounds.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/bttnhca-jaamas-2024/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/s10458-023-09634-5">https://doi.org/10.1007/s10458-023-09634-5</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/bttnhca-jaamas-2024/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/bttnhca-jaamas-2024/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@Article</span><span class="p">{</span><span class="nl">BuzcuTTNHCA2024</span><span class="p">,</span>
<span class="na">author</span><span class="p">=</span><span class="s">{Buzcu, Berk
</span><span class="s"> and Tessa, Melissa
</span><span class="s"> and Tchappi, Igor
</span><span class="s"> and Najjar, Amro
</span><span class="s"> and Hulstijn, Joris
</span><span class="s"> and Calvaresi, Davide
</span><span class="s"> and Aydo{\u{g}}an, Reyhan}</span><span class="p">,</span>
<span class="na">title</span><span class="p">=</span><span class="s">{Towards interactive explanation-based nutrition virtual coaching systems}</span><span class="p">,</span>
<span class="na">journal</span><span class="p">=</span><span class="s">{Autonomous Agents and Multi-Agent Systems}</span><span class="p">,</span>
<span class="na">year</span><span class="p">=</span><span class="s">{2024}</span><span class="p">,</span>
<span class="na">month</span><span class="p">=</span><span class="s">{Jan}</span><span class="p">,</span>
<span class="na">day</span><span class="p">=</span><span class="s">{20}</span><span class="p">,</span>
<span class="na">volume</span><span class="p">=</span><span class="s">{38}</span><span class="p">,</span>
<span class="na">number</span><span class="p">=</span><span class="s">{1}</span><span class="p">,</span>
<span class="na">pages</span><span class="p">=</span><span class="s">{5}</span><span class="p">,</span>
<span class="na">issn</span><span class="p">=</span><span class="s">{1573-7454}</span><span class="p">,</span>
<span class="na">doi</span><span class="p">=</span><span class="s">{10.1007/s10458-023-09634-5}</span><span class="p">,</span>
<span class="na">url</span><span class="p">=</span><span class="s">{https://doi.org/10.1007/s10458-023-09634-5}</span>
<span class="p">}</span>
</code></pre></div>
Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
https://expectation.ehealth.hevs.ch/posts/publications/csamo-csur-2024/Andrea AgiolloAndrea OmiciniFederico SabbatiniGiovanni CiattoMatteo Magnini2024-03-07T00:00:00+01:002024-03-07T14:41:46+01:00
<p>by <a href="mailto:giovanni.ciatto@unibo.it">Giovanni Ciatto</a>, <a href="mailto:f.sabbatini@unibo.it">Federico Sabbatini</a>, <a href="mailto:andrea.agiollo@unibo.it">Andrea Agiollo</a>, <a href="mailto:matteo.magnini@unibo.it">Matteo Magnini</a>, and <a href="mailto:andrea.omicini@unibo.it">Andrea Omicini</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/csamo-csur-2024/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">In this paper we focus on the issue of opacity of sub-symbolic machine-learning predictors by promoting two complementary activities—namely, symbolic knowledge extraction (SKE) and injection (SKI) from and into sub-symbolic predictors. We consider as symbolic any language being intelligible and interpretable for both humans and computers. Accordingly, we propose general meta-models for both SKE and SKI, along with two taxonomies for the classification of SKE/SKI methods. By adopting an eXplainable AI (XAI) perspective, we highlight how such methods can be exploited to either mitigate the aforementioned opacity issue. Our taxonomies are attained by surveying and classifying existing methods from the literature, following a systematic approach, and by generalising the results of previous surveys targeting specific sub-topics of either SKE or SKI alone. More precisely, we analyse 129 methods for SKE and 117 methods for SKI, and we categorise them according to their purpose, operation, expected input/output data and predictor types. For each method, we also indicate the presence/lack of runnable software implementations. Our work may be of interest for data scientists aiming at selecting the most adequate SKE/SKI method for their needs, and also work as suggestions for researchers interested in filling the gaps of the current state of the art, as well as for developers willing to implement SKE/SKI-based technologies.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/csamo-csur-2024/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="http://dx.doi.org/10.1145/3645103">http://dx.doi.org/10.1145/3645103</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/csamo-csur-2024/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/csamo-csur-2024/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">skeislr-acmcs</span><span class="p">,</span>
<span class="na">acm</span> <span class="p">=</span> <span class="s">{3645103}</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Ciatto, Giovanni and Sabbatini, Federico and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1145/3645103}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{ACM Computing Surveys}</span><span class="p">,</span>
<span class="na">keywords</span> <span class="p">=</span> <span class="s">{Logic; Machine learning theory; Hybrid symbolic-numeric methods; Knowledge representation and reasoning}</span><span class="p">,</span>
<span class="na">numpages</span> <span class="p">=</span> <span class="m">34</span><span class="p">,</span>
<span class="na">publisher</span> <span class="p">=</span> <span class="s">{ACM}</span><span class="p">,</span>
<span class="na">scholar</span> <span class="p">=</span> <span class="s">{13701373869146776438}</span><span class="p">,</span>
<span class="na">semanticscholar</span> <span class="p">=</span> <span class="s">{267611660}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://dl.acm.org/doi/10.1145/3645103}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="m">2024</span>
<span class="p">}</span>
</code></pre></div>
Conflict-based negotiation strategy for human-agent negotiation
https://expectation.ehealth.hevs.ch/posts/publications/kba-applsci-2023/Berk BuzcuMehmet Onur KeskinReyhan Aydoğan2024-03-07T00:00:00+01:002024-03-07T15:14:28+01:00
<p>by <a href="mailto:onur.keskin@ozu.edu.tr">Mehmet Onur Keskin</a>, <a href="mailto:berk.buzcu@ozu.edu.tr">Berk Buzcu</a>, and <a href="mailto:reyhan.aydogan@ozyegin.edu.tr">Reyhan Aydoğan</a></p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="abstract"
>
Abstract
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kba-applsci-2023/#abstract" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Abstract" href="#abstract">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<p align="justify">Day by day, human-agent negotiation becomes more and more vital to reach a socially beneficial agreement when stakeholders need to make a joint decision together. Developing agents who understand not only human preferences but also attitudes is a significant prerequisite for this kind of interaction. Studies on opponent modeling are predominantly based on automated negotiation and may yield good predictions after exchanging hundreds of offers. However, this is not the case in human-agent negotiation in which the total number of rounds does not usually exceed tens. For this reason, an opponent model technique is needed to extract the maximum information gained with limited interaction. This study presents a conflict-based opponent modeling technique and compares its prediction performance with the well-known approaches in human-agent and automated negotiation experimental settings. According to the results of human-agent studies, the proposed model outpr erforms them despite the diversity of participants’ negotiation behaviors. Besides, the conflict-based opponent model estimates the entire bid space much more successfully than its competitors in automated negotiation sessions when a small portion of the outcome space was explored. This study may contribute to developing agents that can perceive their human counterparts’ preferences and behaviors more accurately, acting cooperatively and reaching an admissible settlement for joint interests.</p>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-access"
>
How to access
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kba-applsci-2023/#how-to-access" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to access" href="#how-to-access">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<ul>
<li>DOI: <a href="https://doi.org/10.1007/s10489-023-05001-9">https://doi.org/10.1007/s10489-023-05001-9</a></li>
</ul>
<div class="flex align-center gblog-post__anchorwrap">
<h2 id="how-to-cite"
>
How to cite
</h2>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kba-applsci-2023/#how-to-cite" class="gblog-post__anchor clip flex align-center" aria-label="Anchor How to cite" href="#how-to-cite">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="flex align-center gblog-post__anchorwrap">
<h3 id="bibtex"
>
Bibtex
</h3>
<a data-clipboard-text="https://expectation.ehealth.hevs.ch/posts/publications/kba-applsci-2023/#bibtex" class="gblog-post__anchor clip flex align-center" aria-label="Anchor Bibtex" href="#bibtex">
<svg class="gblog-icon gblog_link"><use xlink:href="#gblog_link"></use></svg>
</a>
</div>
<div class="highlight"><pre class="chroma"><code class="language-bibtex" data-lang="bibtex"><span class="nc">@article</span><span class="p">{</span><span class="nl">KeskinBA23</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Mehmet Onur Keskin and
</span><span class="s"> Berk Buzcu and
</span><span class="s"> Reyhan Aydogan}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Conflict-based negotiation strategy for human-agent negotiation}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{Appl. Intell.}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{53}</span><span class="p">,</span>
<span class="na">number</span> <span class="p">=</span> <span class="s">{24}</span><span class="p">,</span>
<span class="na">pages</span> <span class="p">=</span> <span class="s">{29741--29757}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2023}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{https://doi.org/10.1007/s10489-023-05001-9}</span><span class="p">,</span>
<span class="na">doi</span> <span class="p">=</span> <span class="s">{10.1007/S10489-023-05001-9}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Sat, 13 Jan 2024 17:36:05 +0100}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/journals/apin/KeskinBA23.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>