Robust Counterfactual Explanations in Machine Learning: A Survey
Robust Counterfactual Explanations in Machine Learning: A Survey
Junqi Jiang, Francesco Leofante, Antonio Rago, Francesca Toni
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Survey Track. Pages 8086-8094.
https://doi.org/10.24963/ijcai.2024/894
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.
Keywords:
AI Ethics, Trust, Fairness: ETF: Explainability and interpretability
AI Ethics, Trust, Fairness: ETF: Safety and robustness
AI Ethics, Trust, Fairness: ETF: Trustworthy AI
Machine Learning: ML: Explainable/Interpretable machine learning
Machine Learning: ML: Robustness
Machine Learning: ML: Trustworthy machine learning