"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanations
Machine Learning
2022-11-29 v1 Artificial Intelligence
Computers and Society
Abstract
Counterfactual explanations are a popular type of explanation for making the outcomes of a decision making system transparent to the user. Counterfactual explanations tell the user what to do in order to change the outcome of the system in a desirable way. However, it was recently discovered that the recommendations of what to do can differ significantly in their complexity between protected groups of individuals. Providing more difficult recommendations of actions to one group leads to a disadvantage of this group compared to other groups. In this work we propose a model-agnostic method for computing counterfactual explanations that do not differ significantly in their complexity between protected groups.
Keywords
Cite
@article{arxiv.2211.14858,
title = {"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanations},
author = {André Artelt and Barbara Hammer},
journal= {arXiv preprint arXiv:2211.14858},
year = {2022}
}