MedFD: Personalized and Communication-Efficient Federated Distillation for Heterogeneous Medical Image Analysis

Medical Image classification (MIC) in real-world clinical environments demands models that can operate across decentralized, privacy-sensitive institutions while remaining robust to statistical heterogeneity. Federated Learning (FL) offers a promising solution, yet conventional FL methods often suff...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Yuan Sun, Shengfang Sun
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2025-01-01
Serija:	IEEE Access
Teme:	Federated learning knowledge distillation medical image analysis parameter-efficient decomposition personalized learning
Online dostop:	https://ieeexplore.ieee.org/document/11155084/
Oznake:	Označite Brez oznak, prvi označite!