A two-stage federated learning method that progressively trains on low-loss samples first and adds high-loss samples later reduces client drift and improves accuracy under label skew, feature skew, and noisy labels.
Title resolution pending
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
-
Federated Learning with Sample-level Client Drift Mitigation
A two-stage federated learning method that progressively trains on low-loss samples first and adds high-loss samples later reduces client drift and improves accuracy under label skew, feature skew, and noisy labels.