Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling

2026-09-08

AI Summary

为解决联邦边缘学习中的可扩展性瓶颈，提出非相干空中联邦学习协议，利用波形叠加、非相干检测和长期误差反馈方法，减少通信开销并加速收敛。

Abstract

To mitigate the scalability bottleneck in the radio access network (RAN) in federated edge learning (FEEL), over-the-air federated learning (AirFL) exploits waveform superposition over multiple-access channels (MACs) for analog model aggregation. However, coherent AirFL typically relies on stringent PHY-layer conditions such as accurate channel state information (CSI), tight time/frequency synchronization, and frequent transceiver calibration for signal alignment. However, these requirements, if not impossible to be met, incur substantial communication and computation overhead. In this paper, we propose a non-coherent AirFL (NCAirFL) protocol over a broadband single-antenna MAC, leveraging binary dithering, unbiased non-coherent detection, and long-term error feedback to waive the need for instantaneous CSI. For NCAirFL with general smooth non-convex objectives and a constant learning rate, we establish a convergence bound achieving the convergence rate in the same order of $\mathcal{O}(1/\sqrt{T})$ as communication-ideal FedAvg, where $T$ is the total number of communication rounds. To further improve communication efficiency under data and wireless resource heterogeneity, we also derive a lower bound on the expected single-round objective decrease in the global loss conditioned on device scheduling, building upon which a surrogate objective function is obtained for jointly optimal device selection and power control. Experimental results on MNIST and CIFAR-10 corroborate that NCAirFL achieves learning performance close to FedAvg in practical settings, with the proposed device scheduling policy substantially accelerating convergence.

Problem

• Federated Learning
• Non-Coherent
• Over-the-Air
• Channel State Information
• Device Scheduling

Innovation

• non-coherent over-the-air federated learning
• binary dithering
• unbiased non-coherent detection
• long-term error feedback
• device scheduling