Analysis of Total Variation Minimization for Clustered Federated Learning

No Thumbnail Available

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2024

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

European Signal Processing Conference

Abstract

A key challenge in federated learning applications is the statistical heterogeneity of local datasets. Clustered federated learning addresses this challenge by identifying clusters of local datasets that are approximately homogeneous. One recent approach to clustered federated learning is generalized total variation minimization (GTVMin). This approach requires a similarity graph which can be obtained by domain expertise or in a data-driven fashion via graph learning techniques. Under a widely applicable clustering assumption, we derive an upper bound the deviation between GTVMin solutions and their cluster-wise averages.

Description

| openaire: EC/H2020/952410/EU//TALTECH INDUSTRIAL

Keywords

complex networks, convex optimization, distributed algorithms, federated learning, machine learning

Other note

Citation

Jung, A 2024, Analysis of Total Variation Minimization for Clustered Federated Learning . in 32nd European Signal Processing Conference, EUSIPCO 2024 - Proceedings . European Signal Processing Conference, European Signal Processing Conference (EUSIPCO), pp. 1027-1031, European Signal Processing Conference, Lyon, France, 26/08/2024 . < https://arxiv.org/abs/2403.06298 >