FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation

TL;DR

FairSHAP is a transparent preprocessing method that uses Shapley value attribution to identify and modify fairness-critical data instances, improving fairness metrics while maintaining accuracy.

Contribution

It introduces a novel, interpretable data augmentation framework leveraging Shapley values to enhance fairness in machine learning models.

Findings

Significantly improves demographic parity and equality of opportunity

Achieves fairness with minimal data perturbation

Maintains or improves predictive performance

Abstract

Ensuring fairness in machine learning models is critical, particularly in high-stakes domains where biased decisions can lead to serious societal consequences. Existing preprocessing approaches generally lack transparent mechanisms for identifying which features or instances are responsible for unfairness. This obscures the rationale behind data modifications. We introduce FairSHAP, a novel pre-processing framework that leverages Shapley value attribution to improve both individual and group fairness. FairSHAP identifies fairness-critical instances in the training data using an interpretable measure of feature importance, and systematically modifies them through instance-level matching across sensitive groups. This process reduces discriminative risk - an individual fairness metric - while preserving data integrity and model accuracy. We demonstrate that FairSHAP significantly improves demographic parity and equality of opportunity across diverse tabular datasets, achieving fairness gains with minimal data perturbation and, in some cases, improved predictive performance. As a model-agnostic and transparent method, FairSHAP integrates seamlessly into existing machine learning pipelines and provides actionable insights into the sources of bias.Our code is on https://github.com/ZhuMuMu0216/FairSHAP.