상세 보기
초록
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.
키워드
- 제목
- FedDK: Toward Adaptive Personalized Federated Learning via Decoupled Knowledge Transfer Under Heterogeneous Environments
- 저자
- Han, Seungjin; Lee, Changwoo
- 발행일
- 2026
- 유형
- Article
- 저널명
- IEEE Access
- 권
- 14
- 페이지
- 91468 ~ 91478
- 언어
- ENG
- 출판사
- Institute of Electrical and Electronics Engineers Inc.
- 발행국가
- 미국
- 분량
- 11 페이지
- ISSN
- E 2169-3536
P 2169-3536