Knowledge injection of Datalog rules via Neural Network Structuring with KINS

We propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called Knowledge Injection via Network Structuring (KINS). The idea behind our method is to extend NN internal structure with ad-hoc layers built out of 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, involving multiple datasets and predictor types, to demonstrate how KINS can significantly improve the predictive performance of the neural networks it is applied to.

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

evento origine

 CILC 2022

 Special issue: Selected papers from the 37th Italian Conference on Computational Logic (CILC 2022)

rivista o collana

 Journal of Logic and Computation (JLC)

pubblicazione contenitore

 Special Issue “Computational Logic on Prolog's 50th Anniversary: Highlights from CILC 2022” (numero speciale, 2023) — 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)