Logo image
Multi-Output Distributional Fairness via Post-Processing
Preprint   Open access

Multi-Output Distributional Fairness via Post-Processing

Gang Li, Qihang Lin, Ayush Ghosh and Tianbao Yang
arXiv.org
Cornell University
08/31/2024
DOI: 10.48550/arxiv.2409.00553
url
https://doi.org/10.48550/arxiv.2409.00553View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

The post-processing approaches are becoming prominent techniques to enhance machine learning models' fairness because of their intuitiveness, low computational cost, and excellent scalability. However, most existing post-processing methods are designed for task-specific fairness measures and are limited to single-output models. In this paper, we introduce a post-processing method for multi-output models, such as the ones used for multi-task/multi-class classification and representation learning, to enhance a model's distributional parity, a task-agnostic fairness measure. Existing techniques to achieve distributional parity are based on the (inverse) cumulative density function of a model's output, which is limited to single-output models. Extending previous works, our method employs an optimal transport mapping to move a model's outputs across different groups towards their empirical Wasserstein barycenter. An approximation technique is applied to reduce the complexity of computing the exact barycenter and a kernel regression method is proposed for extending this process to out-of-sample data. Our empirical studies, which compare our method to current existing post-processing baselines on multi-task/multi-class classification and representation learning tasks, demonstrate the effectiveness of the proposed approach.
Computer Science - Artificial Intelligence Computer Science - Computers and Society Computer Science - Learning Statistics - Machine Learning

Details

Metrics

21 Record Views
Logo image