一种复杂网络中交连社团的检测方法  

A Method for Detecting the Overlapping Community Structure in Complex Network

作　　者：田生文[1] 邹德文[2] 韩婷婷[1] 马艳萍[1] 

机构地区：[1]鲁东大学计算机科学与技术学院,烟台264025 [2]河北科技师范学院,秦皇岛066004

出　　处：《图书情报工作》2009年第24期97-100,共4页Library and Information Service

摘　　要：针对Palla等人提出的派系过滤算法无法解决复杂网络中非派系内的节点的社团归属问题以及已有的硬划分社团检测算法不能反映复杂网络中社团间重叠的现象,提出一种改进的交连社团检测方法。该方法不仅可以有效地进行社团的检测,而且可以发现社团之间的重叠部分。对一个科研合作网络的实际数据进行仿真,实验结果表明该算法是可行的。Because it is invalid for the clique percolation method （CPM） to uncover the overlapping community structure in the complex network included the node that is not a vertex of a triangle in the network, and the existing methods of detecting community struc-ture, for example GN algorithm, cannot uncover the overlapping communities in complex network, the authors also detect an improved method to detect the overlapping community structure of complex network. The authors also detect the communities for a science collabo-ration complex network, and the experiment results show the efficiency and accuracy.

关 键 词：复杂网络 交连社团 检测 

分 类 号：O157.5[理学—数学]