Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling

1 code implementation • 4 Mar 2024 • Xingyan Chen, Tian Du, Mu Wang, Tiancheng Gu, Yu Zhao, Gang Kou, Changqiao Xu, Dapeng Oliver Wu

To address these issues, we propose a novel federated learning framework called FedCMD, a model decoupling tailored to the Cloud-edge supported federated learning that separates deep neural networks into a body for capturing shared representations in Cloud and a personalized head for migrating data heterogeneity.

Federated Learning