@inproceedings{Marzari:2024,
author = {Marzari, L and Leofante, F and Cicalese, F and Farinelli, A},
publisher = {IOS Press},
title = {Rigorous probabilistic guarantees for robust counterfactual explanations},
url = {http://hdl.handle.net/10044/1/113234},
year = {2024}
}

Download

TY  - CPAPER
AB  - We study the problem of assessing the robustness ofcounterfactual 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 plausiblemodel 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 targetingplausible 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 ingenerating robust explanations, outperforming existing methods on a range of metrics.
AU  - Marzari,L
AU  - Leofante,F
AU  - Cicalese,F
AU  - Farinelli,A
PB  - IOS Press
PY  - 2024///
TI  - Rigorous probabilistic guarantees for robust counterfactual explanations
UR  - http://hdl.handle.net/10044/1/113234
ER  - 

Download