A fast spectral cluster algorithm based on bipartite graph

Author

Han Li-mao ; Xu Sen ; Zhou Tian

Author_Institution

Sch. of Inf. Eng., Yancheng Inst. of Technol., Yancheng, China

Volume

7

fYear

2011

fDate

12-14 Aug. 2011

Firstpage

3461

Lastpage

3464

Abstract

Recently, spectral clustering has been applied successfully in a variety of different areas. While choosing the similarity graph and its parameters for spectral clustering is not a trivial task and its computational complexity is rather high. In this paper we proposed a fast bipartite graph spectral algorithm which uses evidence accumulation method and algebraic transformation method to avoid the above shortcoming. Experiments on real-world document sets demonstrate the effectiveness of the proposed algorithm.

Keywords

algebra; computational complexity; graph theory; pattern clustering; spectral analysis; algebraic transformation method; bipartite graph; computational complexity; evidence accumulation method; spectral cluster algorithm; Bipartite graph; Clustering algorithms; Clustering methods; Eigenvalues and eigenfunctions; Laplace equations; Matrix decomposition; Mutual information; clustering analysis; normalized mutual information; spectral clustering;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on

Conference_Location

Harbin, Heilongjiang

Print_ISBN

978-1-61284-087-1

Type

conf

DOI

10.1109/EMEIT.2011.6023827

Filename

6023827