personalized-fl

This paper proposes FedDualAtt, a personalized federated learning approach for ECG classification that splits transformer attention heads into globally aggregated and locally private branches to handle data heterogeneity across clinical sites. Experiments on the FedCVD benchmark show improved performance over existing methods.

This paper introduces COSMOS, a model-agnostic personalized federated learning framework that uses clustered server models and pseudo-label-only communication. It provides theoretical analysis showing exponential personalization risk contraction and demonstrates superior performance over existing baselines in heterogeneous environments.