On Learning Fairness and Accuracy on Multiple Subgroups

Changjian Shui, Gezheng Xu, Qi CHEN, Jiaqi Li, Charles Ling, Tal Arbel, Boyu Wang, Christian Gagné

Keywords: algorithmic fairness, deep learning, social aspects of machine learning

Abstract: We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.10837/code)