cs.AIOct 30, 2026

Connectivity-Aware Client Selection in Decentralized Federated Learning

Authors: Usevalad Milasheuski, Monica Nicoli, Stefano Savazzi

Organizations: Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milan, Italy · Consiglio Nazionale delle Ricerche, IEIIT institute, 20133 Milan, Italy · Dipartimento di Ingegneria Gestionale, Politecnico di Milano, 20133 Milan, Italy

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 33 percentage points, emerge under strong data heterogeneity on larger, structurally rich graphs, while the total number of transmitted messages is reduced by 50%50\% compared to naive broadcasting.

Figures & tables

Explore similar work

CardsList
  1. Diversity-Aware Client Selection for Communication-Efficient Federated Learning

    Nov 6, 2026Max Halleryd, Sima Sinaei, Viktor Valadi +3Client Selection in Federated LearningFederated Learning

  2. Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning

    Feb 24, 2026Nihal Balivada, Shrey Gupta, Shashank Shreedhar Bhatt +1Client Selection in Federated LearningHeterogeneous Federated Learning

  3. Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning

    May 20, 2026Adda Akram Bendoukha, Heber Hwang Arcolezi, Nesrine Kaaniche +1Client Selection in Federated LearningNon-IID Federated Learning