Fairness Aware Counterfactuals for Subgroups
This work addresses fairness auditing for subgroups, which is important for ensuring equitable outcomes in AI systems, but it appears incremental as it builds on existing notions.
The paper tackles the problem of auditing subgroup fairness in machine learning by introducing FACTS, a framework that generalizes and refines fairness notions and provides an efficient, model-agnostic method for evaluation, demonstrating advantages through experiments on benchmark datasets.
In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a framework for auditing subgroup fairness through counterfactual explanations. We start with revisiting (and generalizing) existing notions and introducing new, more refined notions of subgroup fairness. We aim to (a) formulate different aspects of the difficulty of individuals in certain subgroups to achieve recourse, i.e. receive the desired outcome, either at the micro level, considering members of the subgroup individually, or at the macro level, considering the subgroup as a whole, and (b) introduce notions of subgroup fairness that are robust, if not totally oblivious, to the cost of achieving recourse. We accompany these notions with an efficient, model-agnostic, highly parameterizable, and explainable framework for evaluating subgroup fairness. We demonstrate the advantages, the wide applicability, and the efficiency of our approach through a thorough experimental evaluation of different benchmark datasets.