Active Sampling for Min-Max Fairness

TL;DR

This paper introduces active sampling and reweighting methods to enhance min-max fairness in classification and regression models, focusing on improving performance for disadvantaged groups through targeted data selection.

Contribution

It presents a simple, general approach for optimizing min-max fairness applicable to various models, with theoretical convergence guarantees for convex problems.

Findings

Effective in improving fairness for disadvantaged groups

Convergence guarantees for convex models

Easy to implement and generalizable

Abstract

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization. The key intuition behind our approach is to use at each timestep a datapoint from the group that is worst off under the current model for updating the model. The ease of implementation and the generality of our robust formulation make it an attractive option for improving model performance on disadvantaged groups. For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis, proving the rate of convergence to a min-max fair solution.