PFL-AP: Personalized Federated Learning With Adaptive Affine Calibration and Prototype-Driven Knowledge Fusion for Non-IID Data
Personalized federated learning (PFL) based on model decoupling has emerged as a prominent paradigm for mitigating statistical heterogeneity. However, most existing methods rely on static or oversimplified local representations, neglecting the severe feature misalignment during global aggregation. This inevitably preci...