2 papers
cs.LG2025
FedFusion: Federated Learning with Diversity- and Cluster-Aware Encoders for Robust Adaptation under Label Scarcity
Ferdinand Kahenga, Antoine Bagula, Patrick Sello +1
Federated learning in practice must contend with heterogeneous feature spaces, severe non-IID data, and scarce labels across clients. We present FedFusion, a federated transfer-lea…
cs.LG2025
FedFiTS: Fitness-Selected, Slotted Client Scheduling for Trustworthy Federated Learning in Healthcare AI
Ferdinand Kahenga, Antoine Bagula, Sajal K. Das +1
Federated Learning (FL) has emerged as a powerful paradigm for privacy-preserving model training, yet deployments in sensitive domains such as healthcare face persistent challenges…