FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness
This addresses the need for trustworthy machine learning by providing tools to audit group fairness, though it is incremental as it builds on existing counterfactual explanation methods.
The paper tackled the problem of auditing group fairness in machine learning by introducing FACEGroup, a graph-based framework for generating feasible and actionable group counterfactual explanations, with experiments on benchmark datasets showing effective generation and novel metrics quantifying fairness disparities.
Counterfactual explanations assess unfairness by revealing how inputs must change to achieve a desired outcome. This paper introduces the first graph-based framework for generating group counterfactual explanations to audit group fairness, a key aspect of trustworthy machine learning. Our framework, FACEGroup (Feasible and Actionable Counterfactual Explanations for Group Fairness), models real-world feasibility constraints, identifies subgroups with similar counterfactuals, and captures key trade-offs in counterfactual generation, distinguishing it from existing methods. To evaluate fairness, we introduce novel metrics for both group and subgroup level analysis that explicitly account for these trade-offs. Experiments on benchmark datasets show that FACEGroup effectively generates feasible group counterfactuals while accounting for trade-offs, and that our metrics capture and quantify fairness disparities.