Fairness Constraints in High-Dimensional Generalized Linear Models

TL;DR

This paper introduces a framework for fairness-aware learning in high-dimensional generalized linear models that infers sensitive attributes from auxiliary data, enabling bias mitigation without direct access to sensitive information.

Contribution

It proposes a novel method to incorporate fairness constraints by inferring sensitive attributes, addressing privacy and legal restrictions in fairness interventions.

Findings

The approach effectively reduces bias in models.

It maintains predictive accuracy while enforcing fairness.

Empirical results demonstrate improved fairness metrics.

Abstract

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but privacy and legal restrictions frequently limit their use. To address this challenge, we propose a framework that infers sensitive attributes from auxiliary features and integrates fairness constraints into model training. Our approach mitigates bias while preserving predictive accuracy, offering a practical solution for fairness-aware learning. Empirical evaluations validate its effectiveness, contributing to the advancement of more equitable algorithmic decision-making.