Knowledge injection of Datalog rules via Neural Network Structuring with KINS

   page       BibTeX_logo.png       attach   
Journal of Logic and Computation 33(8), pages 1832–1850
December 2023

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.

keywordsneural network, expalinable AI, symbolic knowledge injection, KINS, PSyKI
origin event
journal or series
book Journal of Logic and Computation (JLC)
container publication
page_white_acrobatSpecial Issue “Computational Logic on Prolog's 50th Anniversary: Highlights from CILC 2022” (special issue, 2023) — Roberta Calegari, Giovanni Ciatto, Andrea Omicini
funding project
wrenchEXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)