构建社会公平的公共模型
Building Socially-Equitable Public Models
AI总结：
针对公共模型仅追求预测准确性与下游智能体多样化目标不匹配的问题，提出结合策略梯度算法的Equitable Objective，以优化模型在异构智能体间的性能公平性。
摘要：
公共模型为各种下游任务提供预测，在各种AI应用中发挥了关键作用，展示了其在准确预测方面的能力。然而，仅强调预测准确性可能无法与下游智能体的多样化最终目标保持一致。认识到公共模型的预测是一种服务，我们主张将下游智能体的目标整合到优化过程中。具体而言，为了解决性能差异并促进训练中异构智能体之间的公平性，我们提出了一种新颖的Equitable Objective。该目标与策略梯度算法相结合，旨在训练公共模型在具有各自独特关注的下游智能体之间产生更公平/均匀的性能分布。理论分析和实证案例研究均证明了我们的方法在提升利用公共模型进行决策的多样化下游智能体之间的性能公平性方面的有效性。代码和数据集已在https://github.com/Ren-Research/Socially-Equitable-Public-Models发布。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
