by Andrea Agiollo, Giovanni Ciatto, and Andrea Omicini
Abstract 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.
by Andrea Agiollo, Giovanni Ciatto, and Andrea Omicini
Abstract 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.
by Giovanni Ciatto, Federico Sabbatini, Andrea Agiollo, Matteo Magnini, and Andrea Omicini
Abstract 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 Andrea Agiollo and Andrea Omicini
Abstract The success of neural networks (NNs) is tightly linked with their architectural design—a complex problem by itself. We here introduce a novel framework leveraging Graph Neural Networks to Generate Neural Networks (GNN2GNN) where powerful NN architectures can be learned out of a set of available architecture-performance pairs. GNN2GNN relies on a three-way adversarial training of GNN, to optimise a generator model capable of producing predictions about powerful NN architectures.
by Andrea Agiollo and Andrea Omicini
Abstract Neuro-symbolic integration of symbolic and subsymbolic techniques represents a fast-growing AI trend aimed at mitigating the issues of neural networks in terms of decision processes, reasoning, and interpretability. Several state-of-the-art neuro-symbolic approaches aim at improving performance, most of them focusing on proving their effectiveness in terms of raw predictive performance and/or reasoning capabilities. Meanwhile, few efforts have been devoted to increasing model trustworthiness, interpretability, and efficiency – mostly due to the complexity of measuring effectively improvements in terms of trustworthiness and interpretability.
by Andrea Agiollo, Luciano C. Siebert, Pradeep K. Murukannaiah and Andrea Omicini
Abstract Although popular and effective, large language models (LLM) are characterised by a performance vs. transparency trade-off that hinders their applicability to sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations recently proposed by the XAI community. However, to the best of our knowledge, a thorough comparison among available explainability techniques is currently missing, mainly for the lack of a general metric to measure their benefits.
by Mattia Passeri, Andrea Agiollo, and Andrea Omicini
Abstract While representing the de-facto framework for enabling distributed training of Machine Learning models, Federated Learning (FL) still suffers convergence issues when non-Independent and Identically Distributed (non-IID) data are considered. In this context, the local model optimisation on different data distributions generate dissimilar updates, which are difficult to aggregate and translate into sub-optimal convergence. To tackle this issues, we propose Peer-Reviewed Federated Learning (PRFL), an extension of the traditional FL training process inspired by the peer-review procedure common in the academic field, where model updates are reviewed by several other clients in the federation before being aggregated at the server-side.
by Andrea Agiollo, Paolo Bellavista, Matteo Mendula and Andrea Omicini
Abstract Federated Learning (FL) represents the de-facto standard paradigm for enabling distributed learning over multiple clients in real-world scenarios. Despite the great strides reached in terms of accuracy and privacy awareness, the real adoption of FL in real-world scenarios, in particular in industrial deployment environments, is still an open thread. This is mainly due to privacy constraints and to the additional complexity stemming from the set of hyperparameters to tune when employing AI techniques on bandwidth-, computing-, and energy-constrained nodes.
by Andrea Agiollo, Luciano Siebert Cavalcante, Pradeep Kumar Murukannaiah and Andrea Omicini
Abstract The expressive power and efectiveness of large language models (LLMs) is going to increasingly push intelligent agents towards sub-symbolic models for natural language processing (NLP) tasks in human–agent interaction. However, LLMs are characterised by a performance vs. transparency trade-of that hinders their applicability to such sensitive scenarios. This is the main reason behind many approaches focusing on local post-hoc explanations, recently proposed by the XAI community in the NLP realm.
