FedSQ stabilizes federated weight averaging under heterogeneous data by fixing binary gating masks derived from a pretrained model's structure while optimizing only quantitative parameters.
Federated learning: Strategies for improving communication efficiency
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Develops biased FL schemes for heterogeneous wireless networks, provides convergence bounds quantifying bias and variance effects, and optimizes the bias-variance trade-off using successive convex approximation.
citing papers explorer
-
FedSQ: Optimized Weight Averaging via Fixed Gating
FedSQ stabilizes federated weight averaging under heterogeneous data by fixing binary gating masks derived from a pretrained model's structure while optimizing only quantitative parameters.
-
Biased Federated Learning under Wireless Heterogeneity
Develops biased FL schemes for heterogeneous wireless networks, provides convergence bounds quantifying bias and variance effects, and optimizes the bias-variance trade-off using successive convex approximation.