ecg-classification

This paper introduces a hybrid quantum-inspired Kolmogorov-Arnold network for privacy-aware federated learning of ECG data, demonstrating reduced parameters and communication costs while improving classification metrics compared to traditional MLP.

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.