Over-the-air federated learning (OTA-FL) exploits the inherent superposition property of wireless channels to integrate the communication and model aggregation. Though a naturally promising framework for wireless federated learning, it requires care to mitigate physical layer impairments. In this work, we consider a heterogeneous edge-intelligent network with different edge device resources and non-i.i.d. user dataset distributions, under a general non-convex learning objective. We leverage the Reconfigurable Intelligent Surface (RIS) technology to augment OTA-FL system over simultaneous time varying uplink and downlink noisy communication channels under imperfect CSI scenario. We propose a cross-layer algorithm that jointly optimizes RIS configuration, communication and computation resources in this general realistic setting. Specifically, we design dynamic local update steps in conjunction with RIS phase shifts and transmission power to boost learning performance. We present a convergence analysis of the proposed algorithm, and show that it outperforms the existing unified approach under heterogeneous system and imperfect CSI in numerical results.

翻译：空中联邦学习利用无线信道的自然叠加特性来整合通信与模型聚合。虽然这是一个具有天然优势的无线联邦学习框架，但仍需谨慎处理以缓解物理层损伤。本文考虑一个异构边缘智能网络，其中包含不同边缘设备资源和非独立同分布的用户数据集分布，并采用一般非凸学习目标。在不完美信道状态信息场景下，我们利用可重构智能表面技术增强同时存在时变上行和下行噪声通信信道的空中联邦学习系统。我们提出一种跨层算法，在该通用实际设置中联合优化RIS配置、通信和计算资源。具体而言，我们设计动态本地更新步骤，并结合RIS相位偏移和传输功率来提升学习性能。我们给出了所提算法的收敛性分析，数值结果表明，在异构系统和不完美CSI条件下，该算法优于现有统一方法。