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

Federico Sabbatini

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.



Talks / Views


•  tags  •  speakers  •  authors  

 2023    2022    2021    2020    2019    2018    2017    2016    2015    2014–1992

•  talks  •  invited  •  seminars  •  lectures  •  tutorials  •  project  •  informal  •  internal  •  panel  •  PhD  •  poster  •  others  


— speakers

— authors

— sort


— language


— context

23rd Workshop "From Objects to Agents" (WOA 2022)

— where

Genova, Italy

— when


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