KINS: Knowledge Injection via Network Structuring


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Matteo Magnini, Giovanni Ciatto, Andrea Omicini

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

Talks

Journals & Series

Events

  • 37th Italian Conference on Computational Logic (CILC 2022) — 29/06/2022–01/07/2022

Publication

— authors

— editors

— status

published

— sort

paper in proceedings

— publication date

2022

— volume

CILC 2022 – Italian Conference on Computational Logic

— series

CEUR Workshop Proceedings / AI*IA Series

— volume

3204

— pages

254–267

— number of pages

14

— location

Bologna, Italy

URLs

original page  |  original PDF  |  open access PDF

identifiers

— DBLP

conf/cilc/MagniniCO22

— IRIS

11585/899494

— Scholar

10469078385425944401

— Scopus

2-s2.0-85138240764

— print ISSN

1613-0073

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY