This paper studies long-term fair machine learning which aims to mitigate group disparity over the long term in sequential decision-making systems. To define long-term fairness, we leverage the temporal causal graph and use the 1-Wasserstein distance between the interventional distributions of different demographic groups at a sufficiently large time step as the quantitative metric. Then, we propose a three-phase learning framework where the decision model is trained on high-fidelity data generated by a deep generative model. We formulate the optimization problem as a performative risk minimization and adopt the repeated gradient descent algorithm for learning. The empirical evaluation shows the efficacy of the proposed method using both synthetic and semi-synthetic datasets.
@article{arxiv.2401.11288,
title = {Long-Term Fair Decision Making through Deep Generative Models},
author = {Yaowei Hu and Yongkai Wu and Lu Zhang},
journal= {arXiv preprint arXiv:2401.11288},
year = {2024}
}