Compressing class prototypes with per-class masks and a sample-count scaling trick cuts communication cost in prototype-based federated learning by up to several times without hurting accuracy.
Model pruning enables efficient federated learning on edge devices
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
-
TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments
Compressing class prototypes with per-class masks and a sample-count scaling trick cuts communication cost in prototype-based federated learning by up to several times without hurting accuracy.