Does Federated Learning (FL) work when both uplink and downlink communications have errors? How much communication noise can FL handle and what is its impact to the learning performance? This work is devoted to answering these practically important questions by explicitly incorporating both uplink and downlink noisy channels in the FL pipeline. We present several novel convergence analyses of FL over simultaneous uplink and downlink noisy communication channels, which encompass full and partial clients participation, direct model and model differential transmissions, and non-independent and identically distributed (IID) local datasets. These analyses characterize the sufficient conditions for FL over noisy channels to have the same convergence behavior as the ideal case of no communication error. More specifically, in order to maintain the O(1/T) convergence rate of FedAvg with perfect communications, the uplink and downlink signal-to-noise ratio (SNR) for direct model transmissions should be controlled such that they scale as O(t^2) where t is the index of communication rounds, but can stay constant for model differential transmissions. The key insight of these theoretical results is a "flying under the radar" principle - stochastic gradient descent (SGD) is an inherent noisy process and uplink/downlink communication noises can be tolerated as long as they do not dominate the time-varying SGD noise. We exemplify these theoretical findings with two widely adopted communication techniques - transmit power control and diversity combining - and further validating their performance advantages over the standard methods via extensive numerical experiments using several real-world FL tasks.
翻译:联邦学习联盟(FL)是否在上链接和下链接通信都有错误? 联邦学习联盟(FL)在上链接和下链接通信有错误时工作? 联邦学习联盟(FL)能处理多少通信噪音,它能对学习成绩产生什么影响? 这项工作致力于回答这些实际重要的问题,明确将上链接和下链接的噪音频道纳入FL管道。 我们对FAvg的O(1/T)融合率与完美通信管道的连接率、同时上链接和下链接的噪音通信频道(SNR)提出了几项新颖的融合分析,包括完全和部分客户参与、直接模式和模式差异传输,以及不独立和同样分布的本地数据集。这些分析为FL对超音频频道的沟通行为与理想的趋同性格。 这些理论结果的关键是“在雷达原则下进行同步的趋同行为 ”, 将FAFAVG(S-S) 长期的信号和下行(S-ral-ral-lick ) 将S-ral-ral-ral-ral-ligal-slink) 用作一种长期的循环。