Long-Term Fair Decision Making through Deep Generative Models
Yaowei Hu, Yongkai Wu, Lu Zhang
Abstract
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.
BibTeX
@article{Hu_Wu_Zhang_2024, title={Long-Term Fair Decision Making through Deep Generative Models}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30215}, DOI={10.1609/aaai.v38i20.30215}, abstractNote={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.}, number={20}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Hu, Yaowei and Wu, Yongkai and Zhang, Lu}, year={2024}, month={Mar.}, pages={22114-22122} }