Asynchronous broadcast-based decentralized learning in sensor networks. Issue 6 (2nd November 2018)

• Record Type: Journal Article
• Authors: Zhao, Liang; Song, Wen-Zhan; Ye, Xiaojing; Gu, Yujie
• Is Part Of: International journal of parallel, emergent and distributed systems. Volume 33:Issue 6(2018)
• Page Start: 589
• Page End: 607
• Publication Date: 2018-11-02
• Subjects: Asynchronous algorithm -- big data -- decentralized learning -- sensor network; Parallel computers -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Computer algorithms -- Periodicals; 004.35
• DOI: 10.1080/17445760.2017.1294690
• Languages: English
• ISSNs: 1744-5760

Abstract

Abstract: In this paper, we study the problem of decentralized learning in sensor networks in which local learners estimate and reach consensus to the quantity of interest inferred globally while communicating only with their immediate neighbours. The main challenge lies in reducing the communication cost in the network, which involves inter-node synchronisation and data exchange. To address this issue, a novel asynchronous broadcast-based decentralized learning algorithm is proposed. Furthermore, we prove that the iterates generated by the developed decentralized method converge to a consensual optimal solution (model). Numerical results demonstrate that it is a promising approach for decentralized learning in sensor networks. Graphical Abstract: The execution model on a decentralized sensor network and the workflow of asynchronous computing.