Clustering-Based Approaches for Symbolic Knowledge Extraction


Federico Sabbatini, Roberta Calegari

Opaque models belonging to the machine learning world are ever more exploited in the most different application areas. These models, acting as black boxes (BB) from the human perspective, cannot be entirely trusted if the application is critical unless there exists a method to extract symbolic and human-readable knowledge out of them.

In this paper we analyse a recurrent design adopted by symbolic knowledge extractors for BB regressors-that is, the creation of rules associated with hypercubic input space regions. We argue that this kind of partitioning may lead to suboptimal solutions when the data set at hand is high-dimensional or does not satisfy symmetric constraints. We then propose a (deep) clustering-based approach to be performed before symbolic knowledge extraction to achieve better performance with data sets of any kind.

(keywords) Explainable AI; Symbolic knowledge extraction; Clustering

Publication

— authors

Federico Sabbatini, Roberta Calegari

— status

accepted with revision

— sort

paper in proceedings

Files

Open Access PDF

View this PDF full screen

You do not have the plugin required to display this PDF file. You can still download it: XLoKR-2022-clustering.pdf

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY