Federated learning with heterogeneous data and models based on global decision boundary distillation

Abstract Data heterogeneity and performance disparities among heterogeneous models are critical challenges in federated learning with heterogeneous data and models, which limit its practical applicability and degrade local model performance. To address these challenges, we propose Federated Learning...

全面介紹

書目詳細資料

發表在:	Journal of King Saud University: Computer and Information Sciences
Main Authors:	Kejun Zhang, Jun Wang, Wenbin Wang, Taiheng Zeng, Pengcheng Li, Xunxi Wang, Tingrui Zhang
格式:	Article
語言:	英语
出版:	Springer 2025-06-01
主題:	Federal learning Data heterogeneity Model heterogeneity Prototype learning
在線閱讀:	https://doi.org/10.1007/s44443-025-00097-0