Knowledge extraction methods are applied to ML-based predictors to attain explainable representations of their operation when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the ex- traction of either lists or trees of rules. Yet, most of them only support supervised learning – and, in particular, classification – tasks. Iter is among the few rule-extraction methods capable of extracting symbolic rules out of sub-symbolic regressors. However, its performance – here intended as the interpretability of the rules it extracts – easily degrades as the complexity of the regression task at hand increases. In this paper we propose GridEx, an extension of the Iter algorithm, aimed at extracting symbolic knowledge – in the form of lists of if-then- else rules – from any sort of sub-symbolic regressor—there including neural networks of arbitrary depth. With respect to Iter, GridEx produces shorter rule lists retaining higher fidelity w.r.t. the original regressor. We report several experiments assessing GridEx performance against Iter and Cart (i.e., decision-tree regressors) used as benchmarks.

GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors

Federico Sabbatini
;
Giovanni Ciatto;Andrea Omicini
2021

Abstract

Knowledge extraction methods are applied to ML-based predictors to attain explainable representations of their operation when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the ex- traction of either lists or trees of rules. Yet, most of them only support supervised learning – and, in particular, classification – tasks. Iter is among the few rule-extraction methods capable of extracting symbolic rules out of sub-symbolic regressors. However, its performance – here intended as the interpretability of the rules it extracts – easily degrades as the complexity of the regression task at hand increases. In this paper we propose GridEx, an extension of the Iter algorithm, aimed at extracting symbolic knowledge – in the form of lists of if-then- else rules – from any sort of sub-symbolic regressor—there including neural networks of arbitrary depth. With respect to Iter, GridEx produces shorter rule lists retaining higher fidelity w.r.t. the original regressor. We report several experiments assessing GridEx performance against Iter and Cart (i.e., decision-tree regressors) used as benchmarks.
Explainable and Transparent AI and Multi-Agent Systems. Third International Workshop, EXTRAAMAS 2021
18
38
Federico Sabbatini, Giovanni Ciatto, Andrea Omicini
File in questo prodotto:
File Dimensione Formato  
extraamas-2021-iter.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 748.22 kB
Formato Adobe PDF
748.22 kB 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: http://hdl.handle.net/11585/834616
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact