The paper investigates two strategies for incorporating heterogeneous node weights in decentralized learning: embedding the weights into local losses to use a doubly stochastic matrix, and keeping the original losses while using a λ‑induced row‑stochastic matrix. By developing a weighted Hilbert‑space framework, the authors derive tighter convergence rates and show that the row‑stochastic matrix becomes self‑adjoint, reducing penalty terms that otherwise amplify consensus error. They provide conditions under which the row‑stochastic design converges faster, even with a smaller spectral gap, and offer topology‑design guidelines based on eigenvalue comparisons.
By Bing Liu, Boao Kong, Limin Lu, Kun Yuan, Chengcheng Zhao
arXiv:2606. 07496v1 Announce Type: new Abstract: Decentralized stochastic optimization is a fundamental paradigm for large-scale learning over networks, where agents communicate only with their neighbors and no central coordinator is required.
By Ming Sun, Kun Yuan
arXiv:2606. 06687v1 Announce Type: new Abstract: We investigate cluster formation, involving the number and composition of clusters, in decentralized federated learning (FL) with heterogeneous machine learning (ML) optimizers.
By Su Wang, Mung Chiang, H. Vincent Poor
arXiv:2602. 02899v2 Announce Type: replace Abstract: Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization.
By Zesen Wang, Mikael Johansson
arXiv:2510. 01377v2 Announce Type: replace-cross Abstract: In this paper, we propose DeMuon, a method for decentralized matrix optimization over a given communication topology.
By Chuan He, Shuyi Ren, Jingwei Mao, Erik G. Larsson
arXiv:2609.14953v1 Announce Type: cross
Abstract: This paper aims to develop new and efficient distributed algorithms for solving a class of monotone inclusions, $0 \in \sum_{i=1}^n (G_ix + T_ix)$, o...
By Nghia Nguyen-Trung, Ion Necoara, Quoc Tran-Dinh
arXiv:2607. 03171v1 Announce Type: cross Abstract: Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process with no risk of single-point failure.
By Arash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio, J\'anos Kert\'esz, M\'arton Karsai
arXiv:2603. 01730v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks.
By Shan Sha, Shenglong Zhou, Xin Wang, Lingchen Kong, Geoffrey Ye Li
arXiv:2610.00446v1 Announce Type: cross
Abstract: As an alternative to the standard geometric analyses, we give an exact, information-theoretic analysis of stochastic gradient descent (SGD) and its v...
By Akshay Balsubramani
The paper presents a decentralized multitask learning framework that learns task relationships directly from distributed data. It introduces a two‑phase strategy: first estimating a generalized graph Laplacian from noisy stochastic gradient iterates, then using the learned graph to facilitate cooperative multitask diffusion learning. The authors provide theoretical analysis of Laplacian estimation error, its impact on steady‑state performance, and a topology sensitivity index, and confirm the benefits of learned task graphs through simulations.
By Zirui Wan, Stefan Vlaski
arXiv:2607. 04170v1 Announce Type: new Abstract: Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training.
By Liyang Yuan, Yibo Yang, Dandan Guo
arXiv:2608. 15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL).
By Lin Yin, Tiejun Lv, Weicai Li, Xi Yu, Xiaoyu He