Time-triggered Federated Learning over Wireless Networks

TL;DR

This paper introduces a time-triggered federated learning algorithm (TT-Fed) designed for wireless networks, which improves convergence and reduces communication overhead compared to existing methods by jointly optimizing user selection and bandwidth.

Contribution

The paper proposes a novel time-triggered FL algorithm that generalizes synchronous and asynchronous FL, with a convergence analysis and an online optimization approach tailored for wireless networks.

Findings

TT-Fed outperforms FedAsync and FedAT in accuracy by up to 12.5% and 5%.

TT-Fed reduces communication overhead significantly.

The convergence upper bound guides the joint optimization of user selection and bandwidth.

Abstract

The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner. However, traditional FL algorithms are based on an event-triggered aggregation, which suffers from stragglers and communication overhead issues. To address these issues, in this paper, we present a time-triggered FL algorithm (TT-Fed) over wireless networks, which is a generalized form of classic synchronous and asynchronous FL. Taking the constrained resource and unreliable nature of wireless communication into account, we jointly study the user selection and bandwidth optimization problem to minimize the FL training loss. To solve this joint optimization problem, we provide a thorough convergence analysis for TT-Fed. Based on the obtained analytical convergence upper bound, the optimization problem is decomposed into tractable sub-problems with respect to each global aggregation round, and finally solved by our proposed online search algorithm. Simulation results show that compared to asynchronous FL (FedAsync) and FL with asynchronous user tiers (FedAT) benchmarks, our proposed TT-Fed algorithm improves the converged test accuracy by up to 12.5% and 5%, respectively, under highly imbalanced and non-IID data, while substantially reducing the communication overhead.