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

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

reference talk

 Hypercube-Based Methods for Symbolic Knowledge Extraction: Towards a Unified Model (WOA 2022, 01/09/2022) — Federico Sabbatini (Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini)

origin event

 WOA 2022

journal or series

 CEUR Workshop Proceedings (CEUR-WS.org)

funding project

 EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)

 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)

reference publication for talk

 Hypercube-Based Methods for Symbolic Knowledge Extraction: Towards a Unified Model (WOA 2022, 01/09/2022) — Federico Sabbatini (Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini)