Quantized Federated Learning under Transmission Delay and Outage Constraints

TL;DR

This paper analyzes the impact of transmission delay and outage on federated learning in wireless networks and proposes a robust resource allocation scheme to mitigate these issues, improving learning performance under practical constraints.

Contribution

It provides the first analysis of FL convergence under non-ideal wireless channels with delay and outage, and introduces FedTOE, a joint resource and quantization scheme for robustness.

Findings

FL convergence is severely affected by outage and quantization errors.

Uniform outage probabilities across clients can alleviate convergence issues.

FedTOE outperforms existing schemes in transmission-limited scenarios.

Abstract

Federated learning (FL) has been recognized as a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the wireless edge while protecting user privacy. Although various communication schemes have been proposed to expedite the FL process, most of them have assumed ideal wireless channels which provide reliable and lossless communication links between the server and mobile clients. Unfortunately, in practical systems with limited radio resources such as constraint on the training latency and constraints on the transmission power and bandwidth, transmission of a large number of model parameters inevitably suffers from quantization errors (QE) and transmission outage (TO). In this paper, we consider such non-ideal wireless channels, and carry out the first analysis showing that the FL convergence can be severely jeopardized by TO and QE, but intriguingly can be alleviated if the clients have uniform outage probabilities. These insightful results motivate us to propose a robust FL scheme, named FedTOE, which performs joint allocation of wireless resources and quantization bits across the clients to minimize the QE while making the clients have the same TO probability. Extensive experimental results are presented to show the superior performance of FedTOE for deep learning-based classification tasks with transmission latency constraints.