Skip to main navigation Skip to search Skip to main content

Fast computation of modularity in agglomerative clustering methods for community discovery

  • Yueping Li
  • , Yunming Ye*
  • , Eric Ke Wang
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we propose a fast method for successive modularity computations in agglomerative clustering for community discovery. Our method is based on a new data structure to maintain two statistical values derived by the definition of modularity between two adjacent (temporary) communities. We prove the correctness and efficiency of the method. Then, we perform it on standard datasets. The experimental results show that our method improves the efficiency significantly.

Original languageEnglish
Pages (from-to)153-164
Number of pages12
JournalInternational Journal of Advancements in Computing Technology
Volume3
Issue number4
DOIs
StatePublished - May 2011
Externally publishedYes

Keywords

  • Algorithm
  • Community discovery
  • Modularity
  • Time complexity

Fingerprint

Dive into the research topics of 'Fast computation of modularity in agglomerative clustering methods for community discovery'. Together they form a unique fingerprint.

Cite this