Asynchronous broadcast-based decentralized learning in sensor networks

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of parallel, emergent and distributed systems Ročník 33; číslo 6; s. 589 - 607
Hlavní autoři: Zhao, Liang, Song, Wen-Zhan, Ye, Xiaojing, Gu, Yujie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Abingdon Taylor & Francis 02.11.2018
Taylor & Francis Ltd
Témata:
Asynchronous algorithm
big data
Communication
Data exchange
decentralized learning
Machine learning
Mathematical models
Networks
Production planning
sensor network
Sensors
ISSN:1744-5760, 1744-5779
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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. The execution model on a decentralized sensor network and the workflow of asynchronous computing.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1744-5760
1744-5779
DOI:10.1080/17445760.2017.1294690