Robust Counterfactual Explanations in Machine Learning: A Survey

TL;DR

This survey reviews the current state of robust counterfactual explanations in machine learning, highlighting challenges, existing solutions, and limitations to ensure valid and reliable algorithmic recourse.

Contribution

It provides a comprehensive overview of robustness issues in counterfactual explanations and analyzes existing methods and their limitations for future research.

Findings

Robust CEs are crucial for valid algorithmic recourse.

Current methods face significant robustness challenges.

The survey identifies gaps and directions for future work.

Abstract

Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this survey, we review works in the rapidly growing area of robust CEs and perform an in-depth analysis of the forms of robustness they consider. We also discuss existing solutions and their limitations, providing a solid foundation for future developments.