Best Papers
 A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities 


Vol. 50,  No. 2, pp. 195-204, Feb.  2025
10.7840/kics.2025.50.2.195


PDF Full-Text
  Abstract

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.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Ryu and H. Yang, "A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 2, pp. 195-204, 2025. DOI: 10.7840/kics.2025.50.2.195.

[ACM Style]

Ji-Hyun Ryu and Heecheol Yang. 2025. A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities. The Journal of Korean Institute of Communications and Information Sciences, 50, 2, (2025), 195-204. DOI: 10.7840/kics.2025.50.2.195.

[KICS Style]

Ji-Hyun Ryu and Heecheol Yang, "A Study on Distributed Learning Algorithm for Heterogeneous Client Settings in Computing Capabilities," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 2, pp. 195-204, 2. 2025. (https://doi.org/10.7840/kics.2025.50.2.195)
Vol. 50, No. 2 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880