Building Socially-Equitable Public Models

Yejia Liu, Jianyi Yang, Pengfei Li, Tongxin Li, Shaolei Ren
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32268-32286, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-liu24bw, title = {Building Socially-Equitable Public Models}, author = {Liu, Yejia and Yang, Jianyi and Li, Pengfei and Li, Tongxin and Ren, Shaolei}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {32268--32286}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/liu24bw/liu24bw.pdf}, url = {https://proceedings.mlr.press/v235/liu24bw.html}, 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.} }
Endnote
%0 Conference Paper %T Building Socially-Equitable Public Models %A Yejia Liu %A Jianyi Yang %A Pengfei Li %A Tongxin Li %A Shaolei Ren %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-liu24bw %I PMLR %P 32268--32286 %U https://proceedings.mlr.press/v235/liu24bw.html %V 235 %X 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.
APA
Liu, Y., Yang, J., Li, P., Li, T. & Ren, S.. (2024). Building Socially-Equitable Public Models. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:32268-32286 Available from https://proceedings.mlr.press/v235/liu24bw.html.

Related Material