Fairness in Multi-Task Learning via Wasserstein Barycenters

TL;DR

This paper introduces a novel method for ensuring fairness in multi-task learning by extending demographic parity using Wasserstein barycenters, providing a closed-form solution and demonstrating its effectiveness on real and synthetic data.

Contribution

We extend the concept of demographic parity to multi-task learning with Wasserstein barycenters, offering a closed-form solution and a data-driven estimation procedure.

Findings

The method effectively promotes fairness in multi-task models.

Numerical experiments validate the approach on synthetic and real datasets.

The approach applies to both regression and classification tasks.

Abstract

Algorithmic Fairness is an established field in machine learning that aims to reduce biases in data. Recent advances have proposed various methods to ensure fairness in a univariate environment, where the goal is to de-bias a single task. However, extending fairness to a multi-task setting, where more than one objective is optimised using a shared representation, remains underexplored. To bridge this gap, we develop a method that extends the definition of Strong Demographic Parity to multi-task learning using multi-marginal Wasserstein barycenters. Our approach provides a closed form solution for the optimal fair multi-task predictor including both regression and binary classification tasks. We develop a data-driven estimation procedure for the solution and run numerical experiments on both synthetic and real datasets. The empirical results highlight the practical value of our post-processing methodology in promoting fair decision-making.