Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations
Open Access
- 16 October 2024
- book chapter
- Published by IOS Press
- p. 1059-1066
Abstract
We study the problem of assessing the robustness of counterfactual explanations for deep learning models. We focus on plausible model shifts altering model parameters and propose a novel framework to reason about the robustness property in this setting. To motivate our solution, we begin by showing for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete. As this (practically) rules out the existence of scalable algorithms for exactly computing robustness, we propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees while preserving scalability. Remarkably, and differently from existing solutions targeting plausible model shifts, our approach does not impose requirements on the network to be analyzed, thus enabling robustness analysis on a wider range of architectures. Experiments on four binary classification datasets indicate that our method improves the state of the art in generating robust explanations, outperforming existing methods on a range of metrics.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Density-based reliable and robust explainer for counterfactual explanationExpert Systems with Applications, 2023
- On the robustness of sparse counterfactual explanations to adverse perturbationsArtificial Intelligence, 2022
- A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential RecommendationsACM Computing Surveys, 2022
- A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial IntelligenceIEEE Access, 2021
- Wilks’ formula applied to computational tools: A practical discussion and verificationAnnals of Nuclear Energy, 2019
- “Should This Loan be Approved or Denied?”: A Large Dataset with Class Assignment GuidelinesJournal of Statistics Education, 2018