Promoting counterfactual robustness through diversity
File(s)
Accepted version
Author(s)
Leofante, Francesco
Potyka, Nico
Type
Conference Paper
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.
Date Issued
2024-03-24
Date Acceptance
2024-12-09
Citation
Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 2024, Vol. 38 No. 19: AAAI-24, pp.21322-21330
ISSN
2159-5399
Publisher
Association for the Advancement of Artificial Intelligence
Start Page
21322
End Page
21330
Journal / Book Title
Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
Volume
Vol. 38 No. 19: AAAI-24
Copyright Statement
Copyright © 2024, Association for the Advancement of Artificial Intelligence.
Source
The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI24)
Publication Status
Published
Start Date
2024-02-20
Finish Date
2024-02-27
Coverage Spatial
Vancouver, Canada