论文标题
联盟有所作为？在联合学习中最大化社会福利
Alliance Makes Difference? Maximizing Social Welfare 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，一些组织可能会尝试获得全球模式，而无需贡献其当地培训能力，从而降低了社会福利。在本文中，我们将跨索洛FL的组织之间的互动建模为公共物品游戏，从理论上则证明存在社会困难，在纳什均衡中未实现最大的社会福利。为了克服这一难题，我们采用了多人多动力零确定（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。由于所有组织都可以采用MMZD策略，因此我们进一步研究了多个组织共同采用MMZD策略组成MMZD联盟（MMZDA）的案例。我们证明，MMZDA策略可以加强对最大社会福利的控制。实验结果验证了MMZD策略有效地获得最大的社会福利，并且MMZDA可以实现更大的最大值。
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 power, lowering the social welfare. In this paper, we model the interactions among organizations in cross-silo FL as a public goods game and theoretically prove that there exists a social dilemma where the maximum social welfare is not achieved in Nash equilibrium. To overcome this 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. Since the MMZD strategy can be adopted by all organizations, we further study the case of multiple organizations jointly adopting the MMZD strategy to form an MMZD Alliance (MMZDA). We prove that the MMZDA strategy can strengthen the control of the maximum social welfare. Experimental results validate that the MMZD strategy is effective in obtaining the maximum social welfare and the MMZDA can achieve a larger maximum value.
