Lightweight Federated Learning over Wireless Edge Networks

TL;DR

This paper introduces a lightweight federated learning framework for wireless edge networks that optimizes transmission power, model pruning, and gradient quantization to improve efficiency and convergence under resource constraints.

Contribution

The paper presents a novel LTFL framework that integrates power control, model pruning, and gradient quantization, with theoretical convergence analysis and practical optimization solutions.

Findings

LTFL reduces communication overhead and energy consumption.

LTFL achieves faster convergence compared to existing methods.

Experimental results demonstrate superior performance on real-world datasets.

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.