点击次数：

论文类型：期刊论文

发表时间：2012-03-15

发表刊物：PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS

收录刊物：SCIE、EI

卷号：391

期号：6

页面范围：2268-2278

ISSN号：0378-4371

关键字：Complex networks; Gaussian kernel similarity matrix; Spectral bisection method; Overlapping nodes

摘要：Community structure discovery in complex networks is a popular issue, and overlapping community structure discovery in academic research has become one of the hot spots. Based on the Gaussian kernel similarity matrix and spectral bisection, this paper proposes a new community structure discovery method. First, by adjusting the Gaussian kernel parameter to change the scale of similarity, we can find the corresponding non-overlapping community structure when the value of the modularity is the largest relatively. Second, the changes of the Gaussian kernel parameter would lead to the unstable nodes jumping off, so with a slight change in method of non-overlapping community discovery, we can find the overlapping community nodes. Finally, synthetic data, karate club and political books datasets are used to test the proposed method, comparing with some other community discovery methods, to demonstrate the feasibility and effectiveness of this method. Crown Copyright (C) 2011 Published by Elsevier B.V. All rights reserved.