HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer

HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer explores A dual-sided framework for stable personalized federated learning that enhances client specificity and global model accuracy through hierarchical alignment and adversarial knowledge transfer.. Commercial viability score: 7/10 in Federated Learning.