One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
复制标题
DOI：
--
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Avrim Blum;Nika Haghtalab;R. L. Phillips;Han Shao
中科院分区：
文献类型：
--
作者：
Avrim Blum;Nika Haghtalab;R. L. Phillips;Han Shao
近年来，联邦学习被认为是一种在大量学习代理之间实现协作的方法。然而，很少有人知道如何合作协议应考虑代理的激励时，分配个人资源的共同学习，以保持这种合作。受博弈论概念的启发，本文介绍了联邦学习中的激励感知学习和数据共享框架。我们的稳定和无嫉妒的平衡捕获的概念合作的代理有兴趣在满足他们的学习目标，同时保持自己的样本收集负担低的存在。例如，在无嫉妒均衡中，没有代理人希望与任何其他代理人交换他们的采样负担，并且在稳定均衡中，没有代理人希望单方面减少他们的采样负担。除了形式化这个框架，我们的贡献包括表征这种平衡的结构特性，证明它们何时存在，并展示如何计算它们。此外，我们比较的样本复杂性的激励意识的合作与最佳合作时，忽略代理的激励。
In recent years, federated learning has been embraced as an approach for bringing about collaboration across large populations of learning agents. However, little is known about how collaboration protocols should take agents' incentives into account when allocating individual resources for communal learning in order to maintain such collaborations. Inspired by game theoretic notions, this paper introduces a framework for incentive-aware learning and data sharing in federated learning. Our stable and envy-free equilibria capture notions of collaboration in the presence of agents interested in meeting their learning objectives while keeping their own sample collection burden low. For example, in an envy-free equilibrium, no agent would wish to swap their sampling burden with any other agent and in a stable equilibrium, no agent would wish to unilaterally reduce their sampling burden. In addition to formalizing this framework, our contributions include characterizing the structural properties of such equilibria, proving when they exist, and showing how they can be computed. Furthermore, we compare the sample complexity of incentive-aware collaboration with that of optimal collaboration when one ignores agents' incentives.