Building Socially-Equitable Public Models

TL;DR

This paper introduces a novel approach to train public models that prioritize fairness and equitable performance among diverse downstream agents, moving beyond mere accuracy to address societal and ethical considerations.

Contribution

It proposes a new Equitable Objective and a policy gradient algorithm to enhance fairness in public models, supported by theoretical analysis and empirical case studies.

Findings

Improved performance equity across downstream agents

Effective fairness enhancement demonstrated in case studies

Theoretical validation of the proposed method

Abstract

Public models offer predictions to a variety of downstream tasks and have played a crucial role in various AI applications, showcasing their proficiency in accurate predictions. However, the exclusive emphasis on prediction accuracy may not align with the diverse end objectives of downstream agents. Recognizing the public model's predictions as a service, we advocate for integrating the objectives of downstream agents into the optimization process. Concretely, to address performance disparities and foster fairness among heterogeneous agents in training, we propose a novel Equitable Objective. This objective, coupled with a policy gradient algorithm, is crafted to train the public model to produce a more equitable/uniform performance distribution across downstream agents, each with their unique concerns. Both theoretical analysis and empirical case studies have proven the effectiveness of our method in advancing performance equity across diverse downstream agents utilizing the public model for their decision-making. Codes and datasets are released at https://github.com/Ren-Research/Socially-Equitable-Public-Models.