Over-the-Air Federated Learning with Phase Noise: Analysis and Countermeasures

2024/01/16 by Martin Dahl, Erik G. Larsson, Dahl, Martin +1 · 2 citations
Computer Science · Engineering · #Distributed #FOS: Computer and information sciences #FOS: Electrical engineering #Ferroelectric and Negative Capacitance Devices #Parallel #Privacy-Preserving Technologies in Data #Signal Processing (eess.SP) #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2401.08183

openalex publication_date 2024/01/16 · openalex created_date 2024/01/18 · openalex updated_date 2026/07/28

Abstract

Wirelessly connected devices can collaborately train a machine learning model using federated learning, where the aggregation of model updates occurs using over-the-air computation. Carrier frequency offset caused by imprecise clocks in devices will cause the phase of the over-the-air channel to drift randomly, such that late symbols in a coherence block are transmitted with lower quality than early symbols. To mitigate the effect of degrading symbol quality, we propose a scheme where one of the permutations Roll, Flip and Sort are applied on gradients before transmission. Through simulations we show that the permutations can both improve and degrade learning performance. Furthermore, we derive the expectation and variance of the gradient estimate, which is shown to grow exponentially with the number of symbols in a coherence block.

Cited by

• Industrial Viewpoints on RAN Technologies for 6G
• On the Distribution of a Two-Dimensional Random Walk with Restricted Angles

Related

• Biased Over-the-Air Federated Learning under Wireless Heterogeneity
• Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
• Approximate Wireless Communication for Federated Learning
• Over-the-Air Federated Learning via Weighted Aggregation
• Timely Parameter Updating in Over-the-Air Federated Learning