Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/75573
Title: Fast community detection in large weighted networks using graphX in the cloud
Authors: Ling, X
Yang, JH
Wang, D 
Chen, JF
Li, LY
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers
Source: 18th IEEE International Conference on High Performance Computing and Communications (HPCC) / 14th IEEE International Conference on Smart City (Smart City) / 2nd IEEE International Conference on Data Science and Systems (DSS), Sydney, Australia, Dec 12-14, 2016, p. 1-8 How to cite?
Abstract: Identification of different communities in large weighted networks is of crucial importance since it helps to uncover priori unknown functional modules such as topics in information networks or cyber-communities in social networks. However, the typical size of networks, such as social network services or World Wide Web, now counts in millions of nodes and is computationally complex. This urgently demands feasible methods and available computing platforms to retrieve their structure efficiently. To address this problem, we propose an algorithm Fast Community Detection (FastCD) based on modularity optimization. Furthermore, FastCD easily supports parallel computation. We implement FastCD with GraphX, which is an embedded graph processing framework built on top of Apache Spark. After carrying out comprehensive experiments in a 16-nodes cluster (32 vCPU) on Amazon EC2, the results indicate that FastCD not only outperforms the state-of-the-art algorithms in terms of computation time, but also guarantees the accuracy of the solutions under different real-world networks commonly used for efficiency comparison.
URI: http://hdl.handle.net/10397/75573
ISBN: 978-1-5090-4297-5
DOI: 10.1109/HPCC-SmartCity-DSS.2016.104
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
Citations as of May 20, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.