Personalizing Federated Learning with Over-the-Air Computations

2023/02/24 by Zihan Chen, Chen, Zihan, Zeshen Li +5
Computer Science · Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #Wireless Communication Security Techniques

paper · pdf · doi:10.48550/arxiv.2302.12509

openalex publication_date 2023/02/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated edge learning is a promising technology to deploy intelligence at the edge of wireless networks in a privacy-preserving manner. Under such a setting, multiple clients collaboratively train a global generic model under the coordination of an edge server. But the training efficiency is often throttled by challenges arising from limited communication and data heterogeneity. This paper presents a distributed training paradigm that employs analog over-the-air computation to address the communication bottleneck. Additionally, we leverage a bi-level optimization framework to personalize the federated learning model so as to cope with the data heterogeneity issue. As a result, it enhances the generalization and robustness of each client's local model. We elaborate on the model training procedure and its advantages over conventional frameworks. We provide a convergence analysis that theoretically demonstrates the training efficiency. We also conduct extensive experiments to validate the efficacy of the proposed framework.

Related

• Federated Learning for Wireless Applications: A Prototype
• Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks
• Towards Scalable Wireless Federated Learning: Challenges and Solutions
• Over-the-Air Federated Learning and Optimization
• Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks