FairGrad and FairGrad* add gradient variance penalties to federated learning, and the authors report these reduce accuracy variance across clients while keeping or improving mean accuracy, though the exact version's gains are inconsistent.
AFed : Algorithmic fair federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FAIRVAR: Fair Federated Learning via Variance Regularization
FairGrad and FairGrad* add gradient variance penalties to federated learning, and the authors report these reduce accuracy variance across clients while keeping or improving mean accuracy, though the exact version's gains are inconsistent.