A federated server that weights client updates by the inverse of each model's validation loss on a small proxy dataset outperforms data-size weighting, but its convergence proof assumes the weight concentration that the method is supposed to provide.
Title resolution pending
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.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
A federated server that weights client updates by the inverse of each model's validation loss on a small proxy dataset outperforms data-size weighting, but its convergence proof assumes the weight concentration that the method is supposed to provide.