Building Socially-Equitable Public Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914824586264576 |
|---|---|
| author | Liu, Yejia Yang, Jianyi Li, Pengfei Li, Tongxin Ren, Shaolei |
| author_facet | Liu, Yejia Yang, Jianyi Li, Pengfei Li, Tongxin Ren, Shaolei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02790 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Building Socially-Equitable Public Models Liu, Yejia Yang, Jianyi Li, Pengfei Li, Tongxin Ren, Shaolei Machine Learning Computers and Society 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. |
| title | Building Socially-Equitable Public Models |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2406.02790 |