FedBiCross clusters clients by model similarity, uses bi-level cross-cluster optimization for adaptive knowledge transfer, and applies personalized distillation to outperform baselines in non-IID data-free one-shot federated learning on medical datasets.
Federated learning with hierarchical clustering of local updates to improve training on non- iid data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FedBiCross: A Bi-Level Optimization Framework to Tackle Non-IID Challenges in Data-Free One-Shot Federated Learning on Medical Data
FedBiCross clusters clients by model similarity, uses bi-level cross-cluster optimization for adaptive knowledge transfer, and applies personalized distillation to outperform baselines in non-IID data-free one-shot federated learning on medical datasets.