AI RESEARCH
HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer
arXiv CS.LG
•
ArXi:2603.24209v1 Announce Type: cross Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shallow prototype alignment and brittle server-side distillation.