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.
Specifically, we used an LLM to assist in refining the language, improving readability, and ensuring clarity in various sections of the paper
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
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.