A Unified Analysis of Federated Learning with Arbitrary Client Participation
Abstract
Federated learning (FL) faces challenges of intermittent client availability and computation/communication efficiency. As a result, only a small subset of clients can participate in FL at a given time. It is important to understand how partial client participation affects convergence, but most existing works have either considered idealized participation patterns or obtained results with non-zero optimality error for generic patterns. In this paper, we provide a unified convergence analysis for FL with arbitrary client participation. We first introduce a generalized version of federated averaging (FedAvg) that amplifies parameter updates at an interval of multiple FL rounds. Then, we present a novel analysis that captures the effect of client participation in a single term. By analyzing this term, we obtain convergence upper bounds for a wide range of participation patterns, including both non-stochastic and stochastic cases, which match either the lower bound of stochastic gradient descent (SGD) or the state-of-the-art results in specific settings. We also discuss various insights, recommendations, and experimental results.
Keywords
Cite
@article{arxiv.2205.13648,
title = {A Unified Analysis of Federated Learning with Arbitrary Client Participation},
author = {Shiqiang Wang and Mingyue Ji},
journal= {arXiv preprint arXiv:2205.13648},
year = {2024}
}
Comments
Presented at NeurIPS 2022. This latest version includes a minor fix of Step (a) in Equation (C.15) in the proof, which only affects a numerical constant in the learning rate choice for the theory. The convergence bounds expressed in $\mathcal{O}(\cdot)$ as well as all the main findings and conclusions remain the same