Generating Robust Counterfactual Explanations
Abstract
Counterfactual explanations have become a mainstay of the XAI field. This particularly intuitive statement allows the user to understand what small but necessary changes would have to be made to a given situation in order to change a model prediction. The quality of a counterfactual depends on several criteria: realism, actionability, validity, robustness, etc. In this paper, we are interested in the notion of robustness of a counterfactual. More precisely, we focus on robustness to counterfactual input changes. This form of robustness is particularly challenging as it involves a trade-off between the robustness of the counterfactual and the proximity with the example to explain. We propose a new framework, CROCO , that generates robust counterfactuals while managing effectively this trade-off, and guarantees the user a minimal robustness. An empirical evaluation on tabular datasets confirms the relevance and effectiveness of our approach.
Cite
Text
Guyomard et al. "Generating Robust Counterfactual Explanations." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023. doi:10.1007/978-3-031-43418-1_24Markdown
[Guyomard et al. "Generating Robust Counterfactual Explanations." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023.](https://mlanthology.org/ecmlpkdd/2023/guyomard2023ecmlpkdd-generating/) doi:10.1007/978-3-031-43418-1_24BibTeX
@inproceedings{guyomard2023ecmlpkdd-generating,
title = {{Generating Robust Counterfactual Explanations}},
author = {Guyomard, Victor and Fessant, Françoise and Guyet, Thomas and Bouadi, Tassadit and Termier, Alexandre},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2023},
pages = {394-409},
doi = {10.1007/978-3-031-43418-1_24},
url = {https://mlanthology.org/ecmlpkdd/2023/guyomard2023ecmlpkdd-generating/}
}