Fair Mixup: Fairness via Interpolation
arXiv:2103.06503
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.
References in corpus (7)
- Equality of Opportunity in Supervised Learning
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Data augmentation instead of explicit regularization
- Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
- Training individually fair ML models with Sensitive Subspace Robustness
- Robust Learning with Jacobian Regularization
- A Distributionally Robust Approach to Fair Classification