Boosting Fair Classifier Generalization through Adaptive Priority Reweighing

TL;DR

This paper introduces an adaptive reweighing technique that enhances the generalization of fair classifiers by focusing on samples near decision boundaries, improving fairness and accuracy across various data modalities.

Contribution

The paper presents a novel adaptive reweighing approach that models sample proximity to decision boundaries, outperforming traditional group-based reweighing methods in fairness and generalization.

Findings

Improves fairness metrics like equal opportunity and demographic parity.

Enhances classifier accuracy on tabular, language, and vision datasets.

Demonstrates better generalization in test scenarios compared to existing methods.

Abstract

With the increasing penetration of machine learning applications in critical decision-making areas, calls for algorithmic fairness are more prominent. Although there have been various modalities to improve algorithmic fairness through learning with fairness constraints, their performance does not generalize well in the test set. A performance-promising fair algorithm with better generalizability is needed. This paper proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability. Most previous reweighing methods propose to assign a unified weight for each (sub)group. Rather, our method granularly models the distance from the sample predictions to the decision boundary. Our adaptive reweighing method prioritizes samples closer to the decision boundary and assigns a higher weight to improve the generalizability of fair classifiers. Extensive experiments are performed to validate the generalizability of our adaptive priority reweighing method for accuracy and fairness measures (i.e., equal opportunity, equalized odds, and demographic parity) in tabular benchmarks. We also highlight the performance of our method in improving the fairness of language and vision models. The code is available at https://github.com/che2198/APW.