Local updates accelerate the DIGing algorithm in distributed optimization, with maximal gains from two updates that depend on network spectral properties.
Decentralized federated learning with gradien t tracking over time-varying directed networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SSD-FL introduces cluster-based segmentation of training rounds, effective loss functions integrating heterogeneous optimizers, and a Cheeger inequality-driven clustering algorithm to improve convergence and communication efficiency in decentralized FL.
citing papers explorer
-
Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects
Local updates accelerate the DIGing algorithm in distributed optimization, with maximal gains from two updates that depend on network spectral properties.
-
Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers
SSD-FL introduces cluster-based segmentation of training rounds, effective loss functions integrating heterogeneous optimizers, and a Cheeger inequality-driven clustering algorithm to improve convergence and communication efficiency in decentralized FL.