FedMHO is a hybrid one-shot federated learning framework where resource-sufficient clients contribute deep classifiers and resource-constrained clients contribute lightweight generative models, fused on the server into a single global model.
Fine-grained preference-aware personalized federated poi recommendation with data sparsity,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices
FedMHO is a hybrid one-shot federated learning framework where resource-sufficient clients contribute deep classifiers and resource-constrained clients contribute lightweight generative models, fused on the server into a single global model.