为快速准确地找到复杂网络的社团划分结果, 引入相似度指标, 提出一种改进的社团划分算法.将网络节点拓扑结构信息作为节点的多维属性, 在不改变网络连边的情况下, 使输入网络转换为节点多属性网络, 并定义节点之间的混合相似度与社团相似度, 运用层次聚类思想得到最终的社团划分结果.在真实网络、计算机生成网络上的实验结果表明, 该算法能够发现明显的社团结构, 并且具有较高的社团划分准确率.%In order to find the result of complex network community division more accurately and quickly, an improved community division algorithm introduced similarity index is proposed. This paper extracts the network node topology information as a multi-dimensional attribute for each node, converts network into a multi attribute network by extracting topology information of nodes without changing the network side, defines the concepts of mixed node similarity and community similarity, and uses the hierarchical clustering idea to get the final community division result. This paper verifies that the algorithm can find the obvious community structure, improve the accuracy rate of community division by experiment on true network and computer generated network.
展开▼
