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. We also report as a concrete example the implementation of the proposed generalisation in the PSyKE framework.

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

Giovanni Ciatto;Roberta Calegari;Andrea Omicini
2022

Abstract

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. We also report as a concrete example the implementation of the proposed generalisation in the PSyKE framework.
Proceedings of the 23rd Workshop "From Objects to Agents"
48
60
Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini
File in questo prodotto:
File Dimensione Formato  
paper4.pdf

accesso aperto

Descrizione: versione finale
Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 1.49 MB
Formato Adobe PDF
1.49 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/899358
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact