Generating robust counterfactual explanations
This work addresses the need for reliable explanations in AI systems, particularly for users requiring actionable insights, though it appears incremental by refining robustness within existing counterfactual methods.
The paper tackles the problem of generating robust counterfactual explanations in XAI, focusing on robustness to input changes, and proposes the CROCO framework to manage the trade-off between robustness and proximity, with empirical evaluation on tabular datasets confirming its effectiveness.
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.