Lightweight Federated Learning over Wireless Edge Networks

2025-07-13

AI Summary

To address the high communication overhead, excessive energy consumption, and unreliable convergence in federated learning (FL) deployment over wireless edge networks, this paper proposes a lightweight joint optimization framework. We establish a closed-form expression for the convergence gap that unifies transmit power control, model pruning, and gradient quantization—marking the first work to jointly optimize these three strategies under dual constraints of latency and energy. Bayesian optimization is further introduced to enable efficient hyperparameter tuning. Extensive experiments on real-world datasets demonstrate that the proposed method reduces communication load by up to 68% and client energy consumption by up to 52% compared to state-of-the-art approaches, while incurring less than 1.2% accuracy degradation. The framework significantly enhances training efficiency and practical feasibility of FL in resource-constrained wireless edge environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

With the exponential growth of smart devices connected to wireless networks, data production is increasing rapidly, requiring machine learning (ML) techniques to unlock its value. However, the centralized ML paradigm raises concerns over communication overhead and privacy. Federated learning (FL) offers an alternative at the network edge, but practical deployment in wireless networks remains challenging. This paper proposes a lightweight FL (LTFL) framework integrating wireless transmission power control, model pruning, and gradient quantization. We derive a closed-form expression of the FL convergence gap, considering transmission error, model pruning error, and gradient quantization error. Based on these insights, we formulate an optimization problem to minimize the convergence gap while meeting delay and energy constraints. To solve the non-convex problem efficiently, we derive closed-form solutions for the optimal model pruning ratio and gradient quantization level, and employ Bayesian optimization for transmission power control. Extensive experiments on real-world datasets show that LTFL outperforms state-of-the-art schemes.

Problem

• Reducing communication overhead in federated learning at wireless edge networks
• Minimizing FL convergence gap with transmission and quantization errors
• Optimizing model pruning and power control under resource constraints

Innovation

• Lightweight FL with power control
• Model pruning and gradient quantization
• Bayesian optimization for power control