Diameter-Constrained Topology Orchestration for Communication-Convergence Tradeoffs in Decentralized Federated Learning
Lists
Only you see this
Abstract
Decentralized federated learning (DFL) is pivotal for the integration of AI and communication in 6G, facilitating distributed edge-network learning without centralized coordination. However, existing DFL frameworks suffer from prohibitive communication overhead and slow convergence, with a critical issue being the difficulty of balancing the tradeoffs between communication efficiency and convergence rates. This paper proposes a novel distributed synchronization topology orchestration method for DFL that leverages the diameter of the communication graph as a tunable parameter to optimize this communication-convergence tradeoff. Our key insight stems from the relationship between the topology diameter and the spectral radius of the consensus matrix, i.e., constraining the diameter reduces the spectral radius, thereby accelerating convergence while minimizing communication costs. Specifically, we formulate the synchronization topology design as a diameter-constrained minimum spanning tree (MST) problem, where the diameter serves as an adjustable parameter to balance the tradeoff. To ensure robustness in dynamic networks, we further devise a distributed adaptation mechanism that maintains the diameterconstrained MST despite node/link failures. Experiments on the CIFAR-10 dataset demonstrate that our method achieves accuracy comparable to fully connected topologies while reducing communication costs by 25% and accelerating convergence by 28% against state-of-the-art benchmarks.
BibTeX
@article{zhang2026diameter,
author = {Chenyu Zhang and Xinchen Lyu and Zixuan Liang and Chenshan Ren and Yanzhao Hou and Qimei Cui},
title = {{Diameter-Constrained Topology Orchestration for Communication-Convergence Tradeoffs in Decentralized Federated Learning}},
journal = {IEEE Transactions on Cognitive Communications and Networking},
year = {2026},
doi = {10.1109/tccn.2026.3656282},
}Loading related content...