A hybrid genetic algorithm and coordinate descent optimization for graph clustering

Author

Ebrahimi, Javid ; Abadeh, Mohammad Saniee

Author_Institution

Fac. of Electr. & Comput. Eng., Tarbiat Modares Univ., Tehran, Iran

fYear

2012

fDate

2-3 May 2012

Firstpage

322

Lastpage

326

Abstract

Graph based clustering has received much attention from researchers in the last decade. In this paper we present a genetic algorithm that is hybridized with a coordinate descent optimization of a novel fuzzy cut objective function. A niching method is integrated to preserve the population diversity and prevent premature convergence. We demonstrate the effectiveness of the proposed approach on several social network and text data sets.

Keywords

convergence; fuzzy set theory; genetic algorithms; pattern clustering; coordinate descent optimization; fuzzy cut objective function; graph based clustering; hybrid genetic algorithm; niching method; population diversity; premature convergence; social network data sets; text data sets; Clustering algorithms; Genetic algorithms; Linear programming; Optimization; Social network services; Sociology; Statistics; clustering; coordinate descent optimization; fuzzy membership; memetic algorithms; niching; normalized cut; relational data;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence and Signal Processing (AISP), 2012 16th CSI International Symposium on

Conference_Location

Shiraz, Fars

Print_ISBN

978-1-4673-1478-7

Type

conf

DOI

10.1109/AISP.2012.6313766

Filename

6313766