FedDK: Toward Adaptive Personalized Federated Learning via Decoupled Knowledge Transfer Under Heterogeneous Environments
IEEE Access · 2026 · 14 · 91468-91478
DOI: 10.1109/access.2026.3703950 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Seungjin Han und 1 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Information and Communications Technology (MSIT), South Korea, National Program for Excellence in Software, Institute of Information and Communications Technology Planning and Evaluation (IITP), in 2026.
Abstract (Originalsprache)
Federated learning (FL) enables collaborative training without sharing raw data; however, its performance typically degrades in heterogeneous client environments due to non-independent and identically distributed (non-IID) data, model disparity, and conflicting objectives between personalization and global generalization. To address this issue, we propose a novel federated decoupled knowledge (FedDK), a personalized FL framework that introduces a dual-head architecture with explicit role separation. FedDK factorizes the output layer into a balanced head that learns from both private supervision and globally distilled knowledge to preserve client-specific adaptation, and a global head that is optimized exclusively with server-aggregated soft targets on proxy data to maintain client-agnostic global knowledge. This decoupled design mitigates optimization interference between local and global objectives while avoiding full parameter exchange via proxy-based knowledge transfer. Extensive experiments on EMNIST, CIFAR-100, and SVHN under strong, intermediate, and weak non-IID settings and cross-domain proxy scenarios, demonstrate that FedDK exhibits high and consistent performance across diverse heterogeneous environments, including domains with very limited proxy data. Overall, FedDK provides a lightweight and practical framework for balancing personalization and global consistency in heterogeneous federated learning.
Förderung
- Ministry of Science and Information and Communications Technology (MSIT), South Korea
- National Program for Excellence in Software
- Institute of Information and Communications Technology Planning and Evaluation (IITP), in 2026
Zitieren
APA
Han, S., & Lee, C. (2026). FedDK: Toward Adaptive Personalized Federated Learning via Decoupled Knowledge Transfer Under Heterogeneous Environments. IEEE Access, 14, 91468-91478. https://doi.org/10.1109/access.2026.3703950
Vancouver
Han S, Lee C. FedDK: Toward Adaptive Personalized Federated Learning via Decoupled Knowledge Transfer Under Heterogeneous Environments. IEEE Access. 2026;14:91468-91478. doi:10.1109/access.2026.3703950
BibTeX
@article{Han2026,
author = {Han, Seungjin and Lee, Changwoo},
title = {FedDK: Toward Adaptive Personalized Federated Learning via Decoupled Knowledge Transfer Under Heterogeneous Environments},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {91468--91478},
doi = {10.1109/access.2026.3703950}
}
EUVIMED