|
|||||
|
|
| 基于结构相似度的大规模社交网络聚类算法 | |
| 引用本文： | 陈季梦, 陈佳俊, 刘杰, 黄亚楼, 王嫄, 冯霞. 基于结构相似度的大规模社交网络聚类算法[J]. 电子与信息学报, 2015, 37(2): 449-454. doi: 10.11999/JEIT140512 |
| 作者姓名： | 陈季梦 陈佳俊 刘杰 黄亚楼 王嫄 冯霞 |
| 作者单位： | 1. 南开大学计算机与控制工程学院天津 300071 2. 南开大学软件学院天津 300071 3. 中国民航大学民航信息技术科研基地天津 300300 |
| 基金项目： | 国家自然科学基金(61105049, 61300166)，中国民航信息技术科研基地开放课题基金(CAAC-ITRB-201303, CAAC-ITRB-201204)，天津市科技计划项目(13ZCZDGX01098)和天津市自然科学基金(14JCQNJC00600)资助课题 |
| 摘 要： | 针对社交网络的有向交互性和大规模特性，该文提出一种基于结构相似度的有向网络聚类算法(DirSCAN)，以及相应的分布式并行算法(PDirSCAN)。考虑社交网络中节点间的有向交互性，将行为结构相似的节点聚集起来，并进行节点功能分析。针对社交网络规模巨大的特点，提出MapReduce框架下的分布式并行聚类算法，在确保聚类结果一致的前提下，提高处理性能。大量真实数据集上的实验结果表明，DirSCAN比无向网络聚类算法(SCAN)在F1上可提高2.34%的性能，并行算法PDirSCAN比DirSCAN运行速度提升1.67倍，能够有效处理大规模的有向网络聚类问题。 |
| 关 键 词： | 社交网络 有向网络聚类 并行算法 MapReduce |
| 收稿时间： | 2014-04-22 |
| 修稿时间： | 2014-08-27 |
Clustering Algorithms for Large-scale Social Networks Based on Structural Similarity |
|
| Chen Ji-Meng, Chen Jia-Jun, Liu Jie, Huang Ya-Lou, Wang Yuan, Feng Xia. Clustering Algorithms for Large-scale Social Networks Based on Structural Similarity[J]. Journal of Electronics & Information Technology, 2015, 37(2): 449-454. doi: 10.11999/JEIT140512 | |
| Authors: | Chen Ji-meng Chen Jia-jun Liu Jie Huang Ya-lou Wang Yuan Feng Xia |
| Affiliation: | (College of Computer and Control Engineering, Nankai University, Tianjin 300071, China) (College of Software, Nankai University, Tianjin 300071, China) (Information Technology Research Base of CAAC, Civil Aviation University of China, Tianjin 300300, China) |
| Abstract: | To cluster the directed and large-scale social networks, a Structural Clustering Algorithm for Directed Networks (DirSCAN) and a corresponding Parallel algorithm (PDirSCAN) are proposed. Considering oriented behavioral relation between two vertices, DirSCAN is constructed based on action structural similarity and function analysis. To meet the need of large-scale social network analysis, a lossless PDirSCAN based on MapReduce distributed parallel architecture is designed to improve the processing performance. A large number of experimental results on real-world network datasets show that DirSCAN improves performance of SCAN up to 2.34% on F1, PDirSCAN runs 1.67 times faster than DirSCAN. |
| Keywords: | Social networks Directed network clustering Parallel algorithm MapReduce |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《电子与信息学报》浏览原始摘要信息 | |
| 点击此处可从《电子与信息学报》下载全文 | |
