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 2306.03401cs.LGcs.DCcs.ITmath.ITmath.OCstat.ML
收藏

一种解决联邦平均中未知参与统计特性的轻量级方法

A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging

IBM T. J. Watson Research Center(IBM TJ沃森研究中心);University of Utah(犹他大学)

Shiqiang Wang, Mingyue Ji

AI总结:

针对联邦学习中客户端参与统计特性未知且现有方法内存开销大的问题,提出基于参与历史自适应加权的轻量算法FedAU,经理论与实验验证其收敛性与性能优势。

摘要:

在联邦学习(FL)中,客户端通常具有先验未知的多样化参与统计特性,若处理不当会严重损害联邦学习的性能。现有针对该问题的研究通常基于全局方差缩减,这类方法需要大量额外内存,内存开销的倍增因子与客户端总数量相等。一个重要的开放问题是,在客户端参与率未知的场景下,找到一种适用于联邦学习的轻量级方法。本文通过根据每个客户端的参与历史调整联邦平均(FedAvg)中的聚合权重,来解决这一问题。我们首先证明,当参与统计特性异质时,采用非最优聚合权重的FedAvg会偏离原始联邦学习目标的最优解,这表明有必要寻找最优聚合权重。然而,当参与统计特性未知时,计算最优权重十分困难。为解决这一问题,我们提出了一种名为FedAU的新算法,该算法无需知晓客户端参与统计特性,通过在线估计最优权重来自适应加权客户端更新,以此改进FedAvg。我们采用一种将估计误差与收敛性相关联的新方法,对FedAU进行了理论收敛性分析。我们的理论结果揭示了重要且有趣的洞见,同时证明FedAU能够收敛至原始目标的最优解,且具备线性加速等理想特性。我们的实验结果也验证了,在多种参与模式下,FedAU相较于基线方法均具有优势。

英文摘要:

In federated learning (FL), clients usually have diverse participation statistics that are unknown a priori, which can significantly harm the performance of FL if not handled properly. Existing works aiming at addressing this problem are usually based on global variance reduction, which requires a substantial amount of additional memory in a multiplicative factor equal to the total number of clients. An important open problem is to find a lightweight method for FL in the presence of clients with unknown participation rates. In this paper, we address this problem by adapting the aggregation weights in federated averaging (FedAvg) based on the participation history of each client. We first show that, with heterogeneous participation statistics, FedAvg with non-optimal aggregation weights can diverge from the optimal solution of the original FL objective, indicating the need of finding optimal aggregation weights. However, it is difficult to compute the optimal weights when the participation statistics are unknown. To address this problem, we present a new algorithm called FedAU, which improves FedAvg by adaptively weighting the client updates based on online estimates of the optimal weights without knowing the statistics of client participation. We provide a theoretical convergence analysis of FedAU using a novel methodology to connect the estimation error and convergence. Our theoretical results reveal important and interesting insights, while showing that FedAU converges to an optimal solution of the original objective and has desirable properties such as linear speedup. Our experimental results also verify the advantage of FedAU over baseline methods with various participation patterns.

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。

↑