Performance Analysis for Resource Constrained Decentralized Federated Learning Over Wireless Networks

TL;DR

This paper analyzes the performance of resource-constrained decentralized federated learning over wireless networks, providing convergence bounds, resource allocation strategies, and simulation validation for digital and analog communication schemes.

Contribution

It offers the first comprehensive convergence analysis and resource optimization strategies for DFL over wireless channels with digital and analog transmission methods.

Findings

Digital transmission resource allocation improves convergence.

Analog transmission performance is affected by channel fading and noise.

Simulations confirm the effectiveness of proposed optimization strategies.

Abstract

Federated learning (FL) can lead to significant communication overhead and reliance on a central server. To address these challenges, decentralized federated learning (DFL) has been proposed as a more resilient framework. DFL involves parameter exchange between devices through a wireless network. This study analyzes the performance of resource-constrained DFL using different communication schemes (digital and analog) over wireless networks to optimize communication efficiency. Specifically, we provide convergence bounds for both digital and analog transmission approaches, enabling analysis of the model performance trained on DFL. Furthermore, for digital transmission, we investigate and analyze resource allocation between computation and communication and convergence rates, obtaining its communication complexity and the minimum probability of correction communication required for convergence guarantee. For analog transmission, we discuss the impact of channel fading and noise on the model performance and the maximum errors accumulation with convergence guarantee over fading channels. Finally, we conduct numerical simulations to evaluate the performance and convergence rate of convolutional neural networks (CNNs) and Vision Transformer (ViT) trained in the DFL framework on fashion-MNIST and CIFAR-10 datasets. Our simulation results validate our analysis and discussion, revealing how to improve performance by optimizing system parameters under different communication conditions.