Rescaled ASGD recovers convergence to the true global objective by rescaling worker stepsizes proportional to computation times, matching the known time lower bound in the leading term under non-convex smoothness and bounded heterogeneity.
Asyncfeded: Asynchronous federated learning with euclidean distance based adaptive weight aggregation.arXiv preprint arXiv:2205.13797
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
FedGMR progressively restores sub-model capacity for bandwidth-constrained clients via gradual density increases and mask-aware aggregation, narrowing the gap to full-model federated learning.
citing papers explorer
-
Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
FedGMR progressively restores sub-model capacity for bandwidth-constrained clients via gradual density increases and mask-aware aggregation, narrowing the gap to full-model federated learning.