arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.13900cs.DC
收藏

学习全局和个性化模型的联邦块坐标下降方案

Federated Block Coordinate Descent Scheme for Learning Global and Personalized Models

Ruiyuan Wu, Anna Scaglione, Hoi-To Wai, Nurullah Karakoc, Kari Hreinsson, Wing-Kin Ma

摘要:

在联邦学习中,模型是从用户的数据中学习的,这些数据在他们的边缘设备中是私有的,通过在服务提供商的“云”中聚合它们来获得全局模型。这样的全球模型具有巨大的商业价值,改善客户的体验。在本文中,我们重点关注现有技术的两个可能改进领域。首先,我们考虑到用户习惯之间的差异,并提出一种基于二次惩罚的公式,用于高效学习全局模型,从而允许个性化局部模型。其次,我们解决了与边缘设备上的异构训练时间相关的延迟问题,不仅利用云和边缘设备之间的分层结构建模通信,而且还在云中。具体来说,我们设计了一个量身定制的块坐标下降为基础的计算方案,伴随着同步和异步云设置的通信协议。我们表征的算法的理论收敛速度,并提供了一个变种,经验表现更好。我们还证明了异步协议,灵感来自多代理共识技术,具有潜在的大的增益延迟相比,同步设置时,边缘设备更新是间歇性的。最后,提供的实验结果不仅证实了理论,而且还表明,与现有技术相比,该系统导致边缘设备上个性化模型的更快收敛。

英文摘要:

In federated learning, models are learned from users' data that are held private in their edge devices, by aggregating them in the service provider's "cloud" to obtain a global model. Such global model is of great commercial value in, e.g., improving the customers' experience. In this paper we focus on two possible areas of improvement of the state of the art. First, we take the difference between user habits into account and propose a quadratic penalty-based formulation, for efficient learning of the global model that allows to personalize local models. Second, we address the latency issue associated with the heterogeneous training time on edge devices, by exploiting a hierarchical structure modeling communication not only between the cloud and edge devices, but also within the cloud. Specifically, we devise a tailored block coordinate descent-based computation scheme, accompanied with communication protocols for both the synchronous and asynchronous cloud settings. We characterize the theoretical convergence rate of the algorithm, and provide a variant that performs empirically better. We also prove that the asynchronous protocol, inspired by multi-agent consensus technique, has the potential for large gains in latency compared to a synchronous setting when the edge-device updates are intermittent. Finally, experimental results are provided that corroborate not only the theory, but also show that the system leads to faster convergence for personalized models on the edge devices, compared to the state of the art.

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。

↑