Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make them unreliable in many contexts. In this paper, we discuss three desirable properties and approaches to quantify them: proximity, connectedness and stability. In addition, we illustrate that there is a risk for post-hoc counterfactual approaches to not satisfy these properties.
@article{arxiv.1906.04774,
title = {Issues with post-hoc counterfactual explanations: a discussion},
author = {Thibault Laugel and Marie-Jeanne Lesot and Christophe Marsala and Marcin Detyniecki},
journal= {arXiv preprint arXiv:1906.04774},
year = {2019}
}
Comments
presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA