Supplementary File: Coded Cooperative Networks for Semi-Decentralized Federated Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Weng, Shudi, Xiao, Ming, Ren, Chao, Skoglund, Mikael
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909500995272704
author Weng, Shudi
Xiao, Ming
Ren, Chao
Skoglund, Mikael
author_facet Weng, Shudi
Xiao, Ming
Ren, Chao
Skoglund, Mikael
contents To enhance straggler resilience in federated learning (FL) systems, a semi-decentralized approach has been recently proposed, enabling collaboration between clients. Unlike the existing semi-decentralized schemes, which adaptively adjust the collaboration weight according to the network topology, this letter proposes a deterministic coded network that leverages wireless diversity for semi-decentralized FL without requiring prior information about the entire network. Furthermore, the theoretical analyses of the outage and the convergence rate of the proposed scheme are provided. Finally, the superiority of our proposed method over benchmark methods is demonstrated through comprehensive simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19002
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Supplementary File: Coded Cooperative Networks for Semi-Decentralized Federated Learning
Weng, Shudi
Xiao, Ming
Ren, Chao
Skoglund, Mikael
Information Theory
To enhance straggler resilience in federated learning (FL) systems, a semi-decentralized approach has been recently proposed, enabling collaboration between clients. Unlike the existing semi-decentralized schemes, which adaptively adjust the collaboration weight according to the network topology, this letter proposes a deterministic coded network that leverages wireless diversity for semi-decentralized FL without requiring prior information about the entire network. Furthermore, the theoretical analyses of the outage and the convergence rate of the proposed scheme are provided. Finally, the superiority of our proposed method over benchmark methods is demonstrated through comprehensive simulations.
title Supplementary File: Coded Cooperative Networks for Semi-Decentralized Federated Learning
topic Information Theory
url https://arxiv.org/abs/2406.19002