Logo image
Back
Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning
Preprint   Open access

Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning

Qi Qi, Quanqi Hu, Qihang Lin and Tianbao Yang
arXiv.org
Cornell University
06/09/2024
DOI: 10.48550/arxiv.2406.05686
url
https://doi.org/10.48550/arxiv.2406.05686View
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

This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive attribute. Adversarial fair representation learning is well suited for this scenario by minimizing a contrastive loss over unlabeled data while maximizing an adversarial loss of predicting the sensitive attribute over the data with sensitive attribute. Nevertheless, optimizing adversarial fair representation learning presents significant challenges due to solving a non-convex non-concave minimax game. The complexity deepens when incorporating a global contrastive loss that contrasts each anchor data point against all other examples. A central question is ``{\it can we design a provable yet efficient algorithm for solving adversarial fair self-supervised contrastive learning}?'' Building on advanced optimization techniques, we propose a stochastic algorithm dubbed SoFCLR with a convergence analysis under reasonable conditions without requring a large batch size. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach for downstream classification with eight fairness notions.
Computer Science - Computer Vision and Pattern Recognition Computer Science - Computers and Society Computer Science - Learning

Details

Metrics

9 Record Views
Logo image