一种新的基于局部相似度的社区发现算法 |
New community detection algorithm based on local similarity |
|
DOI: |
中文关键词: 复杂网络;社区发现;节点相似度;K-means算法 |
英文关键词:complex network;community detection;node similarity;K-means algorithm |
基金项目:教育部人文社会科学研究规划基金(15YJAZH016)和江苏省普通高校研究生创新计划(SJZZ16_0151)资助项目 |
作者 | 单位 | 顾亦然 | 南京邮电大学 自动化学院,江苏南京210023 | 陈雨晴 | 南京邮电大学 自动化学院,江苏南京210023 |
|
摘要点击次数: 769 |
全文下载次数: 1567 |
中文摘要: |
社区发现是复杂网络领域的研究热点问题。为了提高复杂网络中划分社区结构的质量,提出了一种新的基于局部相似度的社区发现算法。首先,考虑到目前研究者们普遍基于共同邻居节点的自身特性来构建局部相似指标,通过引入节点对及其共同邻居间相互联络的亲密程度,定义了新的相似度指标;接着,基于网络节点相似度矩阵,结合改进的K-means算法对网络节点进行相似性聚类,实现网络的社区发现。在真实网络数据重构的网络上进行实验,结果表明,所提算法能够更准确、有效地发现复杂网络中的社区结构。 |
英文摘要: |
Community detection is a hot issue in the field of complex networks.To improve the quality of the community structure in complex networks,a new community detection algorithm based on local node similarity is proposed.Firstly,considering the fact that the researchers generally construct local similarity indexes based on the self-characteristics of the common neighbor nodes,a new similarity index is defined by introducing the degree of aggregation between the node pairs and their common neighbors.Then,the community detection is realized by clustering the network nodes based on the network node similarity matrix and combined with the improved K-means algorithm.The experimental results show that the proposed algorithm can find the community structure in actual networks more accurately and effectively. |
查看全文 查看/发表评论 下载PDF阅读器 |