Saved in:
Bibliographic Details
Main Authors: Li, Yipeng, Lyu, Xinchen
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.03154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929337401344000
author Li, Yipeng
Lyu, Xinchen
author_facet Li, Yipeng
Lyu, Xinchen
contents There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. In this paper, we establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data. The convergence guarantees of SFL are better than that of PFL on heterogeneous data with both full and partial client participation. Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03154
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
Li, Yipeng
Lyu, Xinchen
Machine Learning
There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. In this paper, we establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data. The convergence guarantees of SFL are better than that of PFL on heterogeneous data with both full and partial client participation. Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings.
title Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
topic Machine Learning
url https://arxiv.org/abs/2311.03154