Explaining visual counterfactual explainers
Velazquez Dorta, Diego Alejandro (Centre de Visió per Computador)
Rodríguez López, Pau (Apple)
Lacoste, Alexandre (ServiceNow Research)
Laradji, Issam H. (ServiceNow Research)
Roca i Marvà, Francesc Xavier (Universitat Autònoma de Barcelona)
Gonzàlez, Jordi (Universitat Autònoma de Barcelona)

Additional title:	Evaluating Visual Counterfactual Explainers
Date:	2023
Abstract:	Explainability methods have been widely used to provide insight into the decisions made by statistical models, thus facilitating their adoption in various domains within the industry. Counterfactual explanation methods aim to improve our understanding of a model by perturbing samples in a way that would alter its response in an unexpected manner. This information is helpful for users and for machine learning practitioners to understand and improve their models. Given the value provided by counterfactual explanations, there is a growing interest in the research community to investigate and propose new methods. However, we identify two issues that could hinder the progress in this field. (1) Existing metrics do not accurately reflect the value of an explainability method for the users. (2) Comparisons between methods are usually performed with datasets like CelebA, where images are annotated with attributes that do not fully describe them and with subjective attributes such as ''Attractive''. In this work, we address these problems by proposing an evaluation method with a principled metric to evaluate and compare different counterfactual explanation methods. The evaluation is based on a synthetic dataset where images are fully described by their annotated attributes. As a result, we are able to perform a fair comparison of multiple explainability methods in the recent literature, obtaining insights about their performance. We make the code and data public to the research community.
Grants:	Agencia Estatal de Investigación PID2020-120311RB-I00
Note:	Altres ajuts: this work was supported by the Generalitat de Catalunya under the Industrial Doctorate Program (grant number 2020DI62).
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Published in:	Transactions on Machine Learning Research, (Abril 2023) , ISSN 2835-8856

Adreça alternativa: https://openreview.net/forum?id=RYeRNwRjNE

20 p, 960.7 KB

The record appears in these collections:
Articles > Research articles
Articles > Published articles