Federated Communication-Efficient Multi-Objective Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Askin, Baris, Sharma, Pranay, Joshi, Gauri, Joe-Wong, Carlee
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912336017620992
author Askin, Baris
Sharma, Pranay
Joshi, Gauri
Joe-Wong, Carlee
author_facet Askin, Baris
Sharma, Pranay
Joshi, Gauri
Joe-Wong, Carlee
contents We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or distributed settings. We propose FedCMOO, a novel communication-efficient federated multi-objective optimization (FMOO) algorithm that improves the error convergence performance of the model compared to existing approaches. Unlike prior works, the communication cost of FedCMOO does not scale with the number of objectives, as each client sends a single aggregated gradient to the central server. We provide a convergence analysis of the proposed method for smooth and non-convex objective functions under milder assumptions than in prior work. In addition, we introduce a variant of FedCMOO that allows users to specify a preference over the objectives in terms of a desired ratio of the final objective values. Through extensive experiments, we demonstrate the superiority of our proposed method over baseline approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16398
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Communication-Efficient Multi-Objective Optimization
Askin, Baris
Sharma, Pranay
Joshi, Gauri
Joe-Wong, Carlee
Machine Learning
Distributed, Parallel, and Cluster Computing
We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or distributed settings. We propose FedCMOO, a novel communication-efficient federated multi-objective optimization (FMOO) algorithm that improves the error convergence performance of the model compared to existing approaches. Unlike prior works, the communication cost of FedCMOO does not scale with the number of objectives, as each client sends a single aggregated gradient to the central server. We provide a convergence analysis of the proposed method for smooth and non-convex objective functions under milder assumptions than in prior work. In addition, we introduce a variant of FedCMOO that allows users to specify a preference over the objectives in terms of a desired ratio of the final objective values. Through extensive experiments, we demonstrate the superiority of our proposed method over baseline approaches.
title Federated Communication-Efficient Multi-Objective Optimization
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2410.16398