Hypercube-Based Methods for Symbolic Knowledge Extraction: Towards a Unified Model


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini

Angelo Ferrando, Viviana Mascardi (eds.)
“WOA 2022 – 23rd Workshop “From Objects to Agents””, pages 48–60
CEUR Workshop Proceedings (AIxIA Series) 3261
Sun SITE Central Europe, RWTH Aachen University
November 2022

Symbolic knowledge-extraction (SKE) algorithms proposed by the XAI community to obtain human-intelligible explanations for opaque machine learning predictors are currently being studied and developed with growing interest, also in order to achieve believability in interactions. However, choosing the most adequate extraction procedure amongst the many existing in the literature is becoming more and more challenging, as the amount of available methods increases. In fact, most of the proposed algorithms come with constraints over their applicability.
In this paper we focus upon a quite general class of SKE techniques, namely hypercube-based methods. Despite being commonly considered regression-specific, we discuss why hypercube-based SKE methods are flexible enough to deal with classification problems as well. More generally, we propose a common generalised model for hypercube-based methods, and we show how they can be exploited to perform SKE on datasets, predictors, or learning tasks of any sort.

(keywords) Explainable AI; Knowledge extraction; Interpretable prediction; PSyKE

Talks

Events

  • 23rd Workshop “From Objects to Agents” (WOA 2022) — 01/09/2022–03/09/2022

Publication

— authors

— editors

Angelo Ferrando, Viviana Mascardi

— status

published

— sort

paper in proceedings

— publication date

November 2022

— volume

WOA 2022 – 23rd Workshop “From Objects to Agents”

— series

CEUR Workshop Proceedings / AIxIA Series

— volume

3261

— pages

48–60

— number of pages

13

URLs

original page  |  original PDF  |  open access PDF

identifiers

— DBLP

conf/woa/SabbatiniCCO22

— IRIS

11585/899358

— Scholar

8614662013642803891

— print ISSN

1613-0073

files

Open Access PDF

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