arXiv cs.AI· Usevalad Milasheuski, Monica Nicoli, Stefano Savazzi·· 1 天前AI 评分26
去中心化联邦学习中的连接感知客户端选择
Connectivity-Aware Client Selection in Decentralized Federated Learning
AI 导读
该论文提出用谱图工具做轻量级客户端选择，让去中心化联邦学习中的每个客户端只向结构上最相关的部分邻居发送模型更新，而非全邻域广播。方法利用图拉普拉斯特征向量嵌入与热/扩散核相似度引导选择，在数据强异构、规模较大且结构丰富的图上准确率最高提升约 3 个百分点，同时传输消息总数较朴素广播减少 50%。
正文 · 原文
Abstract:Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server. However, most existing decentralized approaches rely on full-neighborhood broadcasting, where each client transmits its model update to all of its neighbors in each communication round. While effective, this results in significant communication overhead and high energy consumption. This paper applies spectral graph tools as lightweight client selection methods that leverage the graph topology by analyzing the spectral properties of the graph Laplacian over a fixed communication graph. Specifically, we exploit eigenvector embeddings and heat/diffusion kernel similarities to guide each client in selecting only a subset of structurally relevant neighbors, i.e., those that are most beneficial for the convergence of the federation process. This topology aware randomization matches or outperforms uniform neighborhood subsampling and approaches the accuracy of full broadcasting. The largest gains, about $3$ percentage points, emerge under strong data heterogeneity on larger, structurally rich graphs, while the total number of transmitted messages is reduced by $50\%$ compared to naive broadcasting.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41570 [cs.AI] |
| (or arXiv:2610.41570v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41570 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Usevalad Milasheuski [view email]
[v1]
Fri, 30 Oct 2026 11:01:58 UTC (794 KB)
来源：arXiv cs.AI · arxiv.org