Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered. In OTA wireless setups, the adverse channel effects can be alleviated by increasing the number of receive antennas at the parameter server (PS), which performs model aggregation. However, the performance of OTA FL is limited by the presence of mobile users (MUs) located far away from the PS. In this paper, to mitigate this limitation, we propose hierarchical over-the-air federated learning (HOTAFL), which utilizes intermediary servers (IS) to form clusters near MUs. We provide a convergence analysis for the proposed setup, and demonstrate through theoretical and experimental results that local aggregation in each cluster before global aggregation leads to a better performance and faster convergence than OTA FL.
翻译:考虑在无线通信渠道,特别是超空模式汇总框架方面进行联邦学习(FL),在OTA无线设置中,通过增加参数服务器接收天线的数量可以减轻不利的信道效应,因为参数服务器可以进行模型汇总,但是,OTA FL的性能受到远离PS的流动用户(MUs)的存在的限制。在本文中,为了减轻这一限制,我们建议采用跨空联合学习(HOTAFL),利用中间服务器(IS)组成靠近MU的集群。我们为拟议的设置提供了趋同分析,并通过理论和实验结果表明,在全球集合之前,每个集群的本地聚合可以比OTA FL更好地实现业绩和更快的趋同。