Efficient Distributed Clustering Algorithm for Large-Scale Federated Learning 


Vol. 47,  No. 1, pp. 198-205, Jan.  2022
10.7840/kics.2022.47.1.198


PDF
  Abstract

As the use of artificial intelligence increases, privacy issues arise in the process of using data for learning. In the federated learning proposed to solve these issues, learning is performed on a distributed device such as a smartphone, and learning proceeds without exchanging original data between the distributed device and the server. In the federated learning, it is assumed that the data of the participating distributed devices are independent and have the same probability distribution, but since the data distribution of the distributed devices participating in the actual federated learning is non-independent and non-identically, the statistical heterogeneity should be considered. In this paper, we aim to improve the problem of non-independent and non-identically distribution of data in each distributed device in a large-scale federated learning environment. The proposed method uses the weights derived from the learning results of the distributed device, and the simulation results are shown by comparing the accuracy and loss rate performance with existing federated learning.

  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.


  Cite this article

[IEEE Style]

H. Kim, Y. Kim, C. You, H. Park, "Efficient Distributed Clustering Algorithm for Large-Scale Federated Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 198-205, 2022. DOI: 10.7840/kics.2022.47.1.198.

[ACM Style]

Hyungbin Kim, Yongho Kim, Cheolwoo You, and Hyunhee Park. 2022. Efficient Distributed Clustering Algorithm for Large-Scale Federated Learning. The Journal of Korean Institute of Communications and Information Sciences, 47, 1, (2022), 198-205. DOI: 10.7840/kics.2022.47.1.198.

[KICS Style]

Hyungbin Kim, Yongho Kim, Cheolwoo You, Hyunhee Park, "Efficient Distributed Clustering Algorithm for Large-Scale Federated Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 198-205, 1. 2022. (https://doi.org/10.7840/kics.2022.47.1.198)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880