A Survey on Fairness Provision Schemes for Federated Learning Networks 


Vol. 48,  No. 6, pp. 677-680, Jun.  2023
10.7840/kics.2023.48.6.677


PDF
  Abstract

Federated Learning(FL) Network is a method in which terminals lacking artificial intelligence learning resources such as data are connected to a server that supports federated learning to cooperatively complete learning model parameters, and learning performance is improved without directly sending data. an effective way to do it. As federated learning is based on the participation of multiple terminals, issues of fairness are raised in the selection of participants and reflection of weight among participants. In this study, research trends and major algorithms for equity issues in federated learning are introduced. In addition, a scheme to apply the proportional equality equity algorithm is presented.

  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]

Y. Kim and H. Kim, "A Survey on Fairness Provision Schemes for Federated Learning Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 6, pp. 677-680, 2023. DOI: 10.7840/kics.2023.48.6.677.

[ACM Style]

Yeong-chan Kim and Hoon Kim. 2023. A Survey on Fairness Provision Schemes for Federated Learning Networks. The Journal of Korean Institute of Communications and Information Sciences, 48, 6, (2023), 677-680. DOI: 10.7840/kics.2023.48.6.677.

[KICS Style]

Yeong-chan Kim and Hoon Kim, "A Survey on Fairness Provision Schemes for Federated Learning Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 6, pp. 677-680, 6. 2023. (https://doi.org/10.7840/kics.2023.48.6.677)
Vol. 48, No. 6 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