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.
Optimal client sampling for federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.