CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning
This addresses model personalization for clients with heterogeneous data in federated learning, representing an incremental improvement over layer-wise methods.
The paper tackles the challenge of data heterogeneity in federated learning by proposing CD^2-pFed, a framework that uses channel decoupling and cyclic distillation to personalize models, achieving consistent effectiveness across benchmarks like natural and medical image tasks.
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. Despite the recent progress, it remains challenging to deal with heterogeneous data clients, as the discrepant data distributions usually prevent the global model from delivering good generalization ability on each participating client. In this paper, we propose CD^2-pFed, a novel Cyclic Distillation-guided Channel Decoupling framework, to personalize the global model in FL, under various settings of data heterogeneity. Different from previous works which establish layer-wise personalization to overcome the non-IID data across different clients, we make the first attempt at channel-wise assignment for model personalization, referred to as channel decoupling. To further facilitate the collaboration between private and shared weights, we propose a novel cyclic distillation scheme to impose a consistent regularization between the local and global model representations during the federation. Guided by the cyclical distillation, our channel decoupling framework can deliver more accurate and generalized results for different kinds of heterogeneity, such as feature skew, label distribution skew, and concept shift. Comprehensive experiments on four benchmarks, including natural image and medical image analysis tasks, demonstrate the consistent effectiveness of our method on both local and external validations.