Promoting Counterfactual Robustness through Diversity
Francesco Leofante, Nico Potyka
Abstract
Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.
BibTeX
@article{Leofante_Potyka_2024, title={Promoting Counterfactual Robustness through Diversity}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30127}, DOI={10.1609/aaai.v38i19.30127}, abstractNote={Counterfactual explanations shed light on the decisions of black-box models by explaining
how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected).
However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change
in the input can cause a major change in the explanation. This can cause confusion on the user side and
open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be
robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to
be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation
algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the
state-of-the-art in generating robust explanations, while maintaining other desirable properties
and providing competitive computational performance.}, number={19}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Leofante, Francesco and Potyka, Nico}, year={2024}, month={Mar.}, pages={21322-21330} }