메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities
Recommendations
Search
Questions

클라이언트의 서로 다른 학습 능력을 고려한 분산학습 알고리즘 연구

논문 기본 정보

Type
Academic journal
Author
Ji-Hyun Ryu (충남대학교) Heecheol Yang (충남대학교)
Journal
Korea Institute Of Communication Sciences The Journal of Korean Institute of Communications and Information Sciences Vol.50 No.2 KCI Accredited Journals SCOPUS
Published
2025.2
Pages
195 - 204 (10page)
DOI
10.7840/kics.2025.50.2.195

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities
Ask AI
Recommendations
Search
Questions

Abstract· Keywords

Report Errors
In this paper, we address a distributed learning system with a server and clients with heterogeneous computational capabilities. We propose a new distributed learning algorithm that combines split learning with ordered dropout, enabling clients with limited and heterogeneous computing capabilities to participate in training. This approach allows all clients, even with different client-model sizes, to contribute to the improvement of the global model’s performance. We conduct experiments on image classification using ResNet50 on the CIFAR-10 dataset, examining classification performance given the number of clients and the distribution of the dataset. With heterogeneous client settings in computational capacities, simulation results demonstrate that all clients with various client-side model sizes effectively contribute to global model training.

Contents

요약
ABSTRACT
Ⅰ. 서론
Ⅱ. 본론
Ⅲ. 실험
Ⅳ. 결론
References

References (0)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Frequently Viewed Together

Recently viewed articles

Comments(0)

0

Write first comments.

UCI(KEPA) : I410-151-25-02-092293090