Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations

TL;DR

This paper introduces a novel reinforcement learning approach to generate fair counterfactual explanations in AI, ensuring individual and group fairness without sacrificing explanation quality, thus advancing trustworthy and equitable AI decision-making.

Contribution

It formulates fairness in counterfactual explanations at individual, group, and hybrid levels and proposes a model-agnostic method to optimize fairness constraints alongside explanation quality.

Findings

Effectively ensures individual and group fairness in CFs

Maintains high proximity and plausibility of explanations

Quantifies the cost of fairness at different levels

Abstract

Explainable Artificial Intelligence (XAI) is becoming increasingly essential for enhancing the transparency of machine learning (ML) models. Among the various XAI techniques, counterfactual explanations (CFs) hold a pivotal role due to their ability to illustrate how changes in input features can alter an ML model's decision, thereby offering actionable recourse to users. Ensuring that individuals with comparable attributes and those belonging to different protected groups (e.g., demographic) receive similar and actionable recourse options is essential for trustworthy and fair decision-making. In this work, we address this challenge directly by focusing on the generation of fair CFs. Specifically, we start by defining and formulating fairness at: 1) individual fairness, ensuring that similar individuals receive similar CFs, 2) group fairness, ensuring equitable CFs across different protected groups and 3) hybrid fairness, which accounts for both individual and broader group-level fairness. We formulate the problem as an optimization task and propose a novel model-agnostic, reinforcement learning based approach to generate CFs that satisfy fairness constraints at both the individual and group levels, two objectives that are usually treated as orthogonal. As fairness metrics, we extend existing metrics commonly used for auditing ML models, such as equal choice of recourse and equal effectiveness across individuals and groups. We evaluate our approach on three benchmark datasets, showing that it effectively ensures individual and group fairness while preserving the quality of the generated CFs in terms of proximity and plausibility, and quantify the cost of fairness in the different levels separately. Our work opens a broader discussion on hybrid fairness and its role and implications for XAI and beyond CFs.