Decentralized Federated Averaging via Random Walk Article Swipe

MAKE IMPACT

Changheng Wang , Zhiqing Wei , Lizhe Liu , Qiao Deng , Y. Wu , Yangyang Niu , Yashan Pang , Zhiyong Feng · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2508.21286

Federated Learning (FL) is a communication-efficient distributed machine learning method that allows multiple devices to collaboratively train models without sharing raw data. FL can be categorized into centralized and decentralized paradigms. The centralized paradigm relies on a central server to aggregate local models, potentially resulting in single points of failure, communication bottlenecks, and exposure of model parameters. In contrast, the decentralized paradigm, which does not require a central server, provides improved robustness and privacy. The essence of federated learning lies in leveraging multiple local updates for efficient communication. However, this approach may result in slower convergence or even convergence to suboptimal models in the presence of heterogeneous and imbalanced data. To address this challenge, we study decentralized federated averaging via random walk (DFedRW), which replaces multiple local update steps on a single device with random walk updates. Traditional Federated Averaging (FedAvg) and its decentralized versions commonly ignore stragglers, which reduces the amount of training data and introduces sampling bias. Therefore, we allow DFedRW to aggregate partial random walk updates, ensuring that each computation contributes to the model update. To further improve communication efficiency, we also propose a quantized version of DFedRW. We demonstrate that (quantized) DFedRW achieves convergence upper bound of order $\mathcal{O}(\frac{1}{k^{1-q}})$ under convex conditions. Furthermore, we propose a sufficient condition that reveals when quantization balances communication and convergence. Numerical analysis indicates that our proposed algorithms outperform (decentralized) FedAvg in both convergence rate and accuracy, achieving a 38.3\% and 37.5\% increase in test accuracy under high levels of heterogeneities.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2508.21286

PDF

https://arxiv.org/pdf/2508.21286

OA Status

green

OpenAlex ID

https://openalex.org/W4415989258

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415989258

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2508.21286

Digital Object Identifier

Title

Decentralized Federated Averaging via Random Walk

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-08-29

Full publication date if available

Authors

Changheng Wang, Zhiqing Wei, Lizhe Liu, Qiao Deng, Y. Wu, Yangyang Niu, Yashan Pang, Zhiyong Feng

List of authors in order

Landing page

https://arxiv.org/abs/2508.21286

Publisher landing page

PDF URL

https://arxiv.org/pdf/2508.21286

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2508.21286

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload