In this section
@inproceedings{Leofante:2024:10.1609/aaai.v38i19.30127,
author = {Leofante, F and Potyka, N},
doi = {10.1609/aaai.v38i19.30127},
pages = {21322--21330},
publisher = {Association for the Advancement of Artificial Intelligence},
title = {Promoting counterfactual robustness through diversity},
url = {http://dx.doi.org/10.1609/aaai.v38i19.30127},
year = {2024}
}
TY - CPAPER
AB - 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.
AU - Leofante,F
AU - Potyka,N
DO - 10.1609/aaai.v38i19.30127
EP - 21330
PB - Association for the Advancement of Artificial Intelligence
PY - 2024///
SN - 2159-5399
SP - 21322
TI - Promoting counterfactual robustness through diversity
UR - http://dx.doi.org/10.1609/aaai.v38i19.30127
ER -
