Clustering by local label approximation with extreme learning machine

Xiao Zhuo Luo, Fang Liu, Xiao Dong Wang, Zhi Guo Zhou

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Clustering has been an active research area over the last decades, and has become one of most important subjects in pattern recognition and data mining. In recent years, Graph Based Clustering (GBC) has received more attentions. In GBC, as Local Learning based Clustering Algorithm (LLCA) can obtain better cluster performance, it is used widely. However, there are so many parameters in current LLCA method that we have to spend much time on selecting them. To solve this problem, a novel clustering method, named as Clustering by Local Label Approximation with Extreme Learning Machine (LLAELM) is proposed in this paper. As Extreme Learning Machine (ELM) have the advantages of fewer parameters and higher accuracy, it is applied to improve the clustering algorithm based on local learning in the proposed method. The experiments on artificial data sets and UCI data sets demonstrate that LLAELM can obtain better performance than competitive methods.

Original languageEnglish (US)
Pages (from-to)508-515
Number of pages8
JournalInternational Journal of Digital Content Technology and its Applications
Issue number18
StatePublished - Oct 1 2012


  • Clustering
  • Extreme Learning Machine (ELM)
  • Local Learning based Clustering Algorithm (LLCA)

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications


Dive into the research topics of 'Clustering by local label approximation with extreme learning machine'. Together they form a unique fingerprint.

Cite this