Multi-Granular Evaluation of Diverse Counterfactual Explanations

Yining Yuan, Kevin McAreavey, Shujun Li, Weiru Liu

2024

Abstract

As a popular approach in Explainable AI (XAI), an increasing number of counterfactual explanation algorithms have been proposed in the context of making machine learning classifiers more trustworthy and transparent. This paper reports our evaluations of algorithms that can output diverse counterfactuals for one instance. We first evaluate the performance of DiCE-Random, DiCE-KDTree, DiCE-Genetic and Alibi-CFRL, taking XGBoost as the machine learning model for binary classification problems. Then, we compare their suggested feature changes with feature importance by SHAP. Moreover, our study highlights that synthetic counterfactuals, drawn from the input domain but not necessarily the training data, outperform native counter-factuals from the training data regarding data privacy and validity. This research aims to guide practitioners in choosing the most suitable algorithm for generating diverse counterfactual explanations.

Paper Citation

in Harvard Style

Yuan Y., McAreavey K., Li S. and Liu W. (2024). Multi-Granular Evaluation of Diverse Counterfactual Explanations. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 186-197. DOI: 10.5220/0012349900003636

in Bibtex Style

@conference{icaart24,
author={Yining Yuan and Kevin McAreavey and Shujun Li and Weiru Liu},
title={Multi-Granular Evaluation of Diverse Counterfactual Explanations},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2024},
pages={186-197},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012349900003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Multi-Granular Evaluation of Diverse Counterfactual Explanations
SN - 978-989-758-680-4
AU - Yuan Y.
AU - McAreavey K.
AU - Li S.
AU - Liu W.
PY - 2024
SP - 186
EP - 197
DO - 10.5220/0012349900003636
PB - SciTePress