基于相似度动态演化的符号网络社区检测

A Similarity Dynamic Evolutionary Community Detection Method in Signed Network

本文提出一种基于相似度动态演化的符号网络社区检测算法.为了使不连接的两节点之间有相似度,加入了最短路径的相似度计算函数,从而使同一个社区中节点的相似度随着时间的变化更新为1,不同社区之间节点的相似度随着时间的变化更新为-1.在本文所提出网络模型的基础上,整个网络会分为几个不同的社区.为了验证算法的性能,本文针对USC真实网络,GGS真实网络以及17个人工合成网络进行了仿真,并与已有文献作了相关比较,实验结果表明,算法有一定的优势.

A similarity dynamic evolutionary community detection method in signed network has been proposed in this paper.The similarity function based on shortest paths has been added in this paper,so that the similarity values between nodes in same community are updated to l,and the similarity values between nodes in different communities are updated to -1 over time.All of the network will be divided into several clusters based on the proposed network model.In order to verify the performance of the proposed algorithm,this paper has been tested by USC network,GGS network and 17 Synthetic networks.The results showed that our proposed method is efficiently.