A federated learning method combining model-fusion pruning with representation regularization reports modest accuracy gains on two benchmarks while compressing models for heterogeneous devices.
Fedgh: Heterogeneous federated learning with generalized global header
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
A federated learning method combining model-fusion pruning with representation regularization reports modest accuracy gains on two benchmarks while compressing models for heterogeneous devices.