Fairness in Multi-Task Learning via Wasserstein Barycenters
This work addresses fairness for multi-task learning scenarios, which is an underexplored area, though it appears incremental as it builds on existing fairness definitions and methods.
The paper tackles the problem of ensuring algorithmic fairness in multi-task learning, where multiple objectives are optimized using a shared representation, by extending Strong Demographic Parity using multi-marginal Wasserstein barycenters, resulting in a closed-form solution for optimal fair predictors in regression and binary classification tasks.
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.