Best Papers
 Personalized Federated Post-Training for Real-time Adaptation to Label Distribution Shifts 


Vol. 50,  No. 12, pp. 1811-1821, Dec.  2025
10.7840/kics.2025.50.12.1811


PDF Full-Text
  Abstract

Artificial intelligence systems deployed to individual devices are exposed to shifting label distributions over time, degrading model performance. While post-training has been studied to address this, limited local data and overfitting can cause loss of critical knowledge in the pre-trained model. We propose Fed-AFIR(Federated Adaptation with FIM Regularization), leveraging the Fisher Information Matrix (FIM) to preserve critical parameters while enabling collaboration across devices, consistently outperforming existing approaches under dynamic label distribution and heterogeneous device data conditions.

  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]

K. Im, H. Park, M. Kim, M. Joe, M. Kwon, "Personalized Federated Post-Training for Real-time Adaptation to Label Distribution Shifts," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 12, pp. 1811-1821, 2025. DOI: 10.7840/kics.2025.50.12.1811.

[ACM Style]

Kyungjin Im, Heewon Park, Miru Kim, Mugon Joe, and Minhae Kwon. 2025. Personalized Federated Post-Training for Real-time Adaptation to Label Distribution Shifts. The Journal of Korean Institute of Communications and Information Sciences, 50, 12, (2025), 1811-1821. DOI: 10.7840/kics.2025.50.12.1811.

[KICS Style]

Kyungjin Im, Heewon Park, Miru Kim, Mugon Joe, Minhae Kwon, "Personalized Federated Post-Training for Real-time Adaptation to Label Distribution Shifts," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 12, pp. 1811-1821, 12. 2025. (https://doi.org/10.7840/kics.2025.50.12.1811)
Vol. 50, No. 12 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