Article In: scopus, dblp

Benchmarking instance-centric counterfactual algorithms for XAI: from white box to black box

ACM Computing Surveys

Catarina Moreira; Yu-Liang Chou; Joaquim Jorge — 2024 — ACM

Key information

Authors:

Catarina Moreira (Catarina Alexandra Pinto Moreira); Yu-Liang Chou; Chihcheng Hsieh; Chun Ouyang; João Pereira (João António Madeiras Pereira); Joaquim Jorge (Joaquim Armando Pires Jorge)

Published in

June 6, 2024

Abstract

This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.

Publication details

Authors in the community:

Publication version

AM - Accepted manuscript

Publisher

ACM

Link to the publisher's version

https://dl.acm.org/doi/abs/10.1145/3672553

Title of the publication container

ACM Computing Surveys

First page or article number

145:1

Last page

145:37

Volume

57

Issue

6

Fields of Science and Technology (FOS)

computer-and-information-sciences - Computer and information sciences

Publication language (ISO code)

eng - English

Rights type:

Open access

Creative Commons license

CC-BY - Attribution

Financing entity

Fundação para a Ciência e a Tecnologia

Identifier for the funding entity: UIDB/50021/2020