KINS: Knowledge Injection via Network Structuring
by Matteo Magnini, Giovanni Ciatto, and Andrea Omicini
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.
@inproceedings{kins-cilc2022,
author = {Magnini, Matteo and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {CILC 2022 -- Italian Conference on Computational Logic},
dblp = {conf/cilc/MagniniCO22},
editor = {Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea},
iris = {11585/899494},
issn = {1613-0073},
keywords = {neural network; explainable AI; symbolic knowledge injection; KINS; PSyKI},
location = {Bologna, Italy},
numpages = 14,
pages = {254--267},
publisher = {CEUR-WS},
scholar = {10469078385425944401},
scopus = {2-s2.0-85138240764},
series = {CEUR Workshop Proceedings},
subseries = {AI*IA Series},
title = {{KINS}: Knowledge Injection via Network Structuring},
url = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlopenaccess = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
urlpdf = {http://ceur-ws.org/Vol-3204/paper_25.pdf},
volume = 3204,
year = 2022
}