SFedSat combines hierarchical clustering, FixMatch/CutMix semi-supervised learning, staleness-aware aggregation, and adaptive quantization to run federated learning on large LEO satellite constellations with fewer labels and lower communication cost.
Satellite edge intelligence: DRL-based resource management for task inference in LEO-based satellite-ground collaborative networks,
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.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
SFedSat combines hierarchical clustering, FixMatch/CutMix semi-supervised learning, staleness-aware aggregation, and adaptive quantization to run federated learning on large LEO satellite constellations with fewer labels and lower communication cost.