arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.08362cs.GTcs.DC
收藏

联盟会带来差异吗?在跨孤岛联邦学习中最大化社会福利

Alliance Makes Difference? Maximizing Social Welfare in Cross-Silo Federated Learning

Jianan Chen, Qin Hu, Honglu Jiang

AI总结:

本文将跨孤岛联邦学习中组织间的交互建模为公共物品博弈,揭示了纳什均衡下无法实现最大社会福利的困境,并提出采用多人多动作零决定子(MMZD)策略及MMZD联盟(MMZDA)来有效最大化社会福利。

摘要:

作为联邦学习(FL)的典型设置之一,跨孤岛FL允许各组织联合训练一个最优的机器学习(ML)模型。在这种情况下,一些组织可能试图在不贡献其本地训练算力的情况下获取全局模型,从而降低了社会福利。在本文中,我们将跨孤岛FL中各组织之间的交互建模为公共物品博弈,并从理论上证明了存在一种社会困境,即在纳什均衡下无法实现最大社会福利。为了克服这一困境,我们采用多人多动作零决定子(MMZD)策略来最大化社会福利。借助MMZD,单个组织可以无需额外成本地单方面控制社会福利。由于MMZD策略可以被所有组织采用,我们进一步研究了多个组织联合采用MMZD策略以形成MMZD联盟(MMZDA)的情况。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策略在获取最大社会福利方面的有效性,并且MMZDA能够实现更大的最大值。

英文摘要:

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.

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。

↑