FedADP unifies heterogeneous client models in federated learning by dynamically morphing them to a common architecture for aggregation, reporting accuracy improvements of up to 23.3% over FlexiFed.
When deep reinforcement learning meets federated learning: Intelligent multitimescale resource management for multiaccess edge computing in 5g ultradense network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
FedADP unifies heterogeneous client models in federated learning by dynamically morphing them to a common architecture for aggregation, reporting accuracy improvements of up to 23.3% over FlexiFed.