FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness

TL;DR

FACEGroup is a novel graph-based framework that generates feasible, actionable counterfactual explanations for assessing and auditing group fairness in machine learning models, considering real-world constraints and trade-offs.

Contribution

It introduces the first graph-based method for group counterfactual explanations, modeling feasibility constraints and trade-offs, along with new metrics for fairness analysis at group and subgroup levels.

Findings

Effectively generates feasible group counterfactuals.

Captures and quantifies fairness disparities.

Outperforms existing methods on benchmark datasets.

Abstract

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.