A framework combining semantic-aware client selection, heterogeneous model sizes, and feature compression reports 98.5% accuracy and 80.5% less communication on a synthetic 10-client NLP task.
FedNLP: Benchmarking federated learning methods for natural language pro- cessing tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
dataset 1polarities
background 1representative citing papers
citing papers explorer
-
SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks
A framework combining semantic-aware client selection, heterogeneous model sizes, and feature compression reports 98.5% accuracy and 80.5% less communication on a synthetic 10-client NLP task.