PushCen-ADFL is a centroid-based asynchronous federated learning method that applies average-preserving push-sum mixing and regularization to reduce aggregation bias and model drift, claiming up to 6% accuracy gains and 80% lower communication on vision tasks.
Swift: Rapid decentralized federated learning via wait-free model communica- tion,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Simulations identify three operating regimes for decentralized learning convergence under mobility and bandwidth constraints: inter-contact time dictates mixing, partial updates are tolerated with frequent contacts, and dense patterns cause contention.
citing papers explorer
-
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
PushCen-ADFL is a centroid-based asynchronous federated learning method that applies average-preserving push-sum mixing and regularization to reduce aggregation bias and model drift, claiming up to 6% accuracy gains and 80% lower communication on vision tasks.
-
Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints
Simulations identify three operating regimes for decentralized learning convergence under mobility and bandwidth constraints: inter-contact time dictates mixing, partial updates are tolerated with frequent contacts, and dense patterns cause contention.