A Unified Analysis of Federated Learning with Arbitrary Client Participation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Shiqiang, Ji, Mingyue
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917880166088704
author Wang, Shiqiang
Ji, Mingyue
author_facet Wang, Shiqiang
Ji, Mingyue
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2205_13648
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Unified Analysis of Federated Learning with Arbitrary Client Participation
Wang, Shiqiang
Ji, Mingyue
Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
Optimization and Control
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.
title A Unified Analysis of Federated Learning with Arbitrary Client Participation
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Information Theory
Optimization and Control
url https://arxiv.org/abs/2205.13648