Fair Mixup: Fairness via Interpolation

Ching-Yao Chuang, Youssef Mroueh

Keywords: fairness, data augmentation

Abstract: Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups. Nevertheless, even though the constraints are satisfied during training, they might not generalize at evaluation time. To improve the generalizability of fair classifiers, we propose fair mixup, a new data augmentation strategy for imposing the fairness constraint. In particular, we show that fairness can be achieved by regularizing the models on paths of interpolated samples between the groups. We use mixup, a powerful data augmentation strategy to generate these interpolates. We analyze fair mixup and empirically show that it ensures a better generalization for both accuracy and fairness measurement in tabular, vision, and language benchmarks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ chingyaoc/fair-mixup](https://github.com/chingyaoc/fair-mixup)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2103.06503/code)