arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.15166cs.DCcs.LG
收藏

异构数据上分割联邦学习的收敛性分析

Convergence Analysis of Split Federated Learning on Heterogeneous Data

Guangdong University of Technology(广东工业大学);Montclair State University(蒙特克莱尔州立大学);Southern University of Science and Technology(南方科技大学);University of California, Davis(加利福尼亚大学戴维斯分校)

Pengchao Han, Chao Huang, Geng Tian, Ming Tang, Xin Liu

AI总结:

本文针对异构数据下分割联邦学习缺乏收敛保证的问题,分析强凸、一般凸、非凸及客户端缺失情形,给出收敛速率并通过实验证明其优于 FL 与 SL。

摘要:

分割联邦学习(SFL)是近期提出的一种用于多个客户端之间协同模型训练的分布式方法。在 SFL 中,全局模型通常被划分为两个部分:各客户端以并行联邦方式训练其中一部分,主服务器训练另一部分。尽管近期已有关于 SFL 算法开发的研究,但文献中仍缺少对 SFL 的收敛性分析,本文旨在填补这一空白。由于客户端与主服务器之间可能存在双节奏更新,对 SFL 的分析可能比对联邦学习(FL)的分析更具挑战性。我们针对异构数据上的强凸目标函数和一般凸目标函数给出了 SFL 的收敛性分析,其收敛速率分别为 $O(1/T)$ 和 $O(1/\sqrt[3]{T})$,其中 $T$ 表示 SFL 训练的总轮数。我们进一步将分析扩展到非凸目标函数,以及训练期间部分客户端可能不可用的情形。实验验证了我们的理论结果,并表明当大量客户端之间的数据具有高度异构性时,SFL 的表现优于 FL 和分割学习(SL)。

英文摘要:

Split federated learning (SFL) is a recent distributed approach for collaborative model training among multiple clients. In SFL, a global model is typically split into two parts, where clients train one part in a parallel federated manner, and a main server trains the other. Despite the recent research on SFL algorithm development, the convergence analysis of SFL is missing in the literature, and this paper aims to fill this gap. The analysis of SFL can be more challenging than that of federated learning (FL), due to the potential dual-paced updates at the clients and the main server. We provide convergence analysis of SFL for strongly convex and general convex objectives on heterogeneous data. The convergence rates are $O(1/T)$ and $O(1/\sqrt[3]{T})$, respectively, where $T$ denotes the total number of rounds for SFL training. We further extend the analysis to non-convex objectives and the scenario where some clients may be unavailable during training. Experimental experiments validate our theoretical results and show that SFL outperforms FL and split learning (SL) when data is highly heterogeneous across a large number of clients.

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。

↑