KINS: Knowledge Injection via Network Structuring

   Info_icon.svg   data    Eye_icon.svg   attachments    BibTeX_logo.svg   bibtex
Roberta Calegari, Giovanni Ciatto, Andrea Omicini (eds.)
CILC 2022 – Italian Conference on Computational Logic, pages 254–267
CEUR Workshop Proceedings (AI*IA Series) 3204
CEUR-WS
2022

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.

keywords   neural network, explainable AI, symbolic knowledge injection, KINS, PSyKI
reference talk
Talk_icon.svg KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini
origin event
journal or series
Journal_icon.svg CEUR Workshop Proceedings (CEUR-WS.org)
container publication
Publication_icon.svg CILC 2022 – Italian Conference on Computational Logic (edited volume, 2022) — Roberta Calegari, Giovanni Ciatto, Andrea Omicini
funding project
Project_icon.svg EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)
works as
reference publication for talk
Talk_icon.svg KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini