复杂网络社区挖掘综述  

Community Mining in Complex Networks

作　　者：刘大有[1,2] 金弟[3] 何东晓[1,2] 黄晶[1,2] 杨建宁[1,2] 杨博[1,2] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]符号计算与知识工程教育部重点实验室(吉林大学),长春130012 [3]天津大学计算机科学与技术学院,天津300072

出　　处：《计算机研究与发展》2013年第10期2140-2154,共15页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61133011;61202308;61303110;61373053);教育部新世纪优秀人才支持计划基金项目(NCET-11-0204);符号计算与知识工程教育部重点实验室开放基金项目(93K172013K02);天津大学自主创新基金项目(2013XQ-0136);吉林大学科学前沿与交叉学科创新项目(450060481084)

摘　　要：复杂网络社区挖掘是近10年来多学科交叉的前沿研究热点之一,其研究不仅有重要的理论意义,而且有广泛的应用前景.介绍了社区挖掘及重叠社区挖掘的研究背景和研究意义,分析了研究现状,讨论了该研究所面临的一些主要问题及未来的发展方向.同时,为了对不同的社区挖掘算法进行更好地评估,选择了有代表性的6个社区挖掘算法和3个重叠社区挖掘算法进行测试,并给出了对比分析结果,试图为这个新兴研究领域勾画出一个较为全面和清晰的轮廓.Many complex systems in the real world exist in the form of networks, such as social networks, biological networks, Web networks, etc, which are collectively named complex networks. The research of complex networks has attracted many researchers from different fields such as physics, mathematics, computer science, among others. One of the main problems in the study of Complex network is the detection of community structure, i.e. the division of a network into groups of nodes with dense intra-connections and sparse inter-connections, which has recently triggered great interest. The ability to detect community structure has a large amount of usefulness in many aspects. Furthermore, community structure may provide insights in understanding some uncharacteristic properties of a complex network system. For instance, in the World Wide Web, community analysis has uncovered thematic clusters~ in biochemical or neural networks, communities may be functional groups and separating the network into such groups could simplify functional analysis considerably. This paper reviews the background, the significance and the state-of-the-art in discovering （overlapping） communities. Also, it raises several open issues as the conclusion. Here we try to draw a comprehensive overview for this emerging scientific area, with the purpose of offering some beneficial suggestions for related researchers.

关 键 词：复杂网络 社区结构 社区挖掘 重叠社区挖掘 网络聚类 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]