We introduce a general model for explainable Artificial Intelligence that identifies an explanation of a Machine Learning method by classification rules. We define a notion of distance between two Machine Learning methods, and provide a method that computes a set of classification rules that, in turn, approximates another black box method to a given extent. We further build upon this method an anytime algorithm that returns the best approximation it can compute within a given interval of time. This anytime method returns the minimum and maximum difference in terms of approximation provided by the algorithm and uses it to determine whether the obtained approximation is acceptable. We then illustrate the results of a few experiments on three different datasets that show certain properties of the approximations that should be considered while modelling such systems. On top of this, we design a methodology for constructing approximations for ML, that we compare to the no-methods approach typically used in current studies on the explainable artificial intelligence topic.

Classification Rules Explain Machine Learning

Cristani, Matteo
Membro del Collaboration Group
;
Workneh, Tewabe
Membro del Collaboration Group
;
Pasetto, Luca
Membro del Collaboration Group
;
Tomazzoli, Claudio
Membro del Collaboration Group
2022-01-01

Abstract

We introduce a general model for explainable Artificial Intelligence that identifies an explanation of a Machine Learning method by classification rules. We define a notion of distance between two Machine Learning methods, and provide a method that computes a set of classification rules that, in turn, approximates another black box method to a given extent. We further build upon this method an anytime algorithm that returns the best approximation it can compute within a given interval of time. This anytime method returns the minimum and maximum difference in terms of approximation provided by the algorithm and uses it to determine whether the obtained approximation is acceptable. We then illustrate the results of a few experiments on three different datasets that show certain properties of the approximations that should be considered while modelling such systems. On top of this, we design a methodology for constructing approximations for ML, that we compare to the no-methods approach typically used in current studies on the explainable artificial intelligence topic.
2022
Anytime Methods
Machine Learning
eXplainable AI
Approximation
Anytime Methods
File in questo prodotto:
File Dimensione Formato  
109273.pdf

solo utenti autorizzati

Descrizione: paper
Tipologia: Versione dell'editore
Licenza: Copyright dell'editore
Dimensione 327.53 kB
Formato Adobe PDF
327.53 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11562/1120051
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact