KINS: Knowledge Injection via Network Structuring

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.

parole chiave   neural network, explainable AI, symbolic knowledge injection, KINS, PSyKI

presentazione di riferimento

 KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini (Matteo Magnini, Giovanni Ciatto, Andrea Omicini)

evento origine

 CILC 2022

rivista o collana

 CEUR Workshop Proceedings (CEUR-WS.org)

pubblicazione contenitore

 CILC 2022 – Italian Conference on Computational Logic (curatela, 2022) — Roberta Calegari, Giovanni Ciatto, Andrea Omicini

progetto finanziatore

 EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)

pubblicazione di riferimento per presentazione

 KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini (Matteo Magnini, Giovanni Ciatto, Andrea Omicini)