FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
This addresses fairness issues in AI systems for tabular data, which is an incremental improvement over existing contrastive learning approaches.
The authors tackled bias in tabular data by introducing a contrastive learning framework that strategically selects positive pairs and uses supervised and self-supervised methods, resulting in significantly reduced bias compared to existing state-of-the-art models with minimal accuracy trade-off.
As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperative. As evidenced in numerous research studies, learning fair and robust representations has proven to be a powerful approach to effectively debiasing algorithms and improving fairness while maintaining essential information for prediction tasks. Representation learning frameworks, particularly those that utilize self-supervised and contrastive learning, have demonstrated superior robustness and generalizability across various domains. Despite the growing interest in applying these approaches to tabular data, the issue of fairness in these learned representations remains underexplored. In this study, we introduce a contrastive learning framework specifically designed to address bias and learn fair representations in tabular datasets. By strategically selecting positive pair samples and employing supervised and self-supervised contrastive learning, we significantly reduce bias compared to existing state-of-the-art contrastive learning models for tabular data. Our results demonstrate the efficacy of our approach in mitigating bias with minimum trade-off in accuracy and leveraging the learned fair representations in various downstream tasks.