论文标题
联合学习的社会福利最大化
Social Welfare Maximization in Cross-Silo Federated Learning
论文作者
论文摘要
作为联合学习（FL）的典型设置之一，Cross-Silo FL允许组织共同培训最佳机器学习（ML）模型。在这种情况下，一些组织可能会试图在不贡献本地培训的情况下获得全球模型，从而降低社会福利。在本文中，我们首次将Cross-Silo FL组织之间的互动作为公共物品游戏，并从理论上证明存在社会困难，在NASH均衡中未实现最大的社会福利。为了克服这一社会困境，我们采用了多人多动作零确定（MMZD）策略来最大化社会福利。在MMZD的帮助下，单个组织可以单方面控制社会福利，而无需额外费用。实验结果证明了MMZD策略可有效地提高社会福利。
As one of the typical settings of Federated Learning (FL), cross-silo FL allows organizations to jointly train an optimal Machine Learning (ML) model. In this case, some organizations may try to obtain the global model without contributing their local training, lowering the social welfare. In this paper, we model the interactions among organizations in cross-silo FL as a public goods game for the first time and theoretically prove that there exists a social dilemma where the maximum social welfare is not achieved in Nash equilibrium. To overcome this social dilemma, we employ the Multi-player Multi-action Zero-Determinant (MMZD) strategy to maximize the social welfare. With the help of the MMZD, an individual organization can unilaterally control the social welfare without extra cost. Experimental results validate that the MMZD strategy is effective in maximizing the social welfare.
