Achieving Fairness at No Utility Cost via Data Reweighing with Influence

TL;DR

This paper introduces a data reweighing method that achieves fairness in machine learning models without sacrificing utility by modeling individual sample influence and optimizing weights accordingly.

Contribution

The paper proposes a granular influence-based reweighing approach that attains fairness without utility loss, unlike previous uniform reweighing methods.

Findings

Achieves fairness at no utility cost on real datasets.

Empirically demonstrates cost-free fairness for equal opportunity.

Outperforms baseline reweighing methods in experiments.

Abstract

With the fast development of algorithmic governance, fairness has become a compulsory property for machine learning models to suppress unintentional discrimination. In this paper, we focus on the pre-processing aspect for achieving fairness, and propose a data reweighing approach that only adjusts the weight for samples in the training phase. Different from most previous reweighing methods which usually assign a uniform weight for each (sub)group, we granularly model the influence of each training sample with regard to fairness-related quantity and predictive utility, and compute individual weights based on influence under the constraints from both fairness and utility. Experimental results reveal that previous methods achieve fairness at a non-negligible cost of utility, while as a significant advantage, our approach can empirically release the tradeoff and obtain cost-free fairness for equal opportunity. We demonstrate the cost-free fairness through vanilla classifiers and standard training processes, compared to baseline methods on multiple real-world tabular datasets. Code available at https://github.com/brandeis-machine-learning/influence-fairness.