JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE) ›› 2013, Vol. 43 ›› Issue (5): 13-18.

• Articles • Previous Articles     Next Articles

Distributed affinity propagation clustering algorithm based on GraphLab

CHEN Wen-qiang1, LIN Chen1,2, CHEN Ke3, CHEN Jin-xiu1, ZOU Quan1,2*   

  1. 1. School of Information Science and Technology, Xiamen University, Xiamen 361005, China;
    2. Shenzhen Research Institute,  Xiamen University, Shenzhen 518057, China;
    3. Department of Computer Science and Technology, Guangdong University of
    Petrochemical Technology, Maoming 525000, China
  • Received:2013-05-14 Online:2013-10-20 Published:2013-05-14

Abstract:

A distributed affinity propagation algorithm based on GraphLab was proposed, which was named GStrAP (Graphlab based stream affinity propagation). In GraphLab′s DAG abstraction, the parallel computation was represented as a directed acyclic graph with data flowing along edges between vertices, and the “Gather-Apply-Scatter” paradigm was applied to complete data synchronization and algorithm′s iteration. The experimental results on 3D Clusters, Aggregation, Flame and Pathbased datasets with different scale and the clustering performance were compared with Kmeans, which demonstrated that the proposed GStrAP could achieve high performance on both scalability and accuracy.

Key words: distributed computation, affinity propagation clustering algorithm, GraphLab, clustering ensemble

CLC Number: 

  • TP301
[1] DONG Hongbin, ZHANG Guangjiang, PANG Jinwei, HAN Qilong. A clustering ensemble algorithm based on co-evolution [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2015, 45(2): 1-9.
Viewed
Full text
386
HTML PDF
Just accepted Online first Issue Just accepted Online first Issue
0 0 0 0 0 386

  From Others local
  Times 29 357
  Rate 8% 92%

Abstract
778
Just accepted Online first Issue
0 0 778
  From Others
  Times 778
  Rate 100%

Cited

Web of Science  Crossref   ScienceDirect  Search for Citations in Google Scholar >>
 
This page requires you have already subscribed to WoS.
  Shared   
  Discussed   
No Suggested Reading articles found!