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

   Info_icon.svg   dati    Eye_icon.svg   allegati    BibTeX_logo.svg   bibtex
Angelo Ferrando, Viviana Mascardi (a cura di)
WOA 2022 – 23rd Workshop “From Objects to Agents”, pp. 48–60
CEUR Workshop Proceedings (AIxIA Series) 3261
Sun SITE Central Europe, RWTH Aachen University
novembre 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.

parole chiave   Explainable AI, Knowledge extraction, Interpretable prediction, PSyKE
presentazione di riferimento
evento origine
rivista o collana
Journal_icon.svg CEUR Workshop Proceedings (CEUR-WS.org)
progetto finanziatore
Project_icon.svg EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)
Project_icon.svg StairwAI — Stairway to AI: Ease the Engagement of Low-Tech users to the AI-on-Demand platform through AI (01/01/2021–31/12/2023)
prodotto
Product_icon.svg PSyKE
funge da
pubblicazione di riferimento per presentazione