一种基于混合相似性指标的网络动态链路预测方法  

Dynamic Link Prediction Method of Social Network Based on the Mixed Similarity Index

作　　者：陈莎[1] 朱福喜[1] 阳小兰[2] 刘世超[1] 

机构地区：[1]武汉大学计算机学院,武汉430072 [2]武昌理工学院信息工程学院,武汉430223

出　　处：《小型微型计算机系统》2016年第8期1798-1801,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61272277)资助;湖北省自然科学基金项目(2014CFB356)资助

摘　　要：社会网络中节点属性等外部信息的不可靠性及难获取性,使得社会网络的链路预测方法都集中在网络的拓扑结构信息上,并且常用的链路预测方法往往只利用了网络的局部拓扑信息.此外,社会网络的静态链路预测方法忽视了网络演化趋势信息,影响了预测精度.基于以上现状,结合节点间共同邻居相似性指标及偏好连接相似性指标,提出一种基于混合相似性指标的网络动态链路预测方法.该方法提出一种基于网络局部信息的混合相似性指标,为已存在链接分配一个影响力衰减因子并将其引入混合相似性指标进行计算,进而根据该混合相似性指标预测链路.实验结果表明用上述方法,预测精度得到了提高.Node attributes and other external information are unreliable and hard to obtain, which makes the the link prediction methods of social network focuses on the information of network topology, and the frequently-used link prediction methods only used the local topology information of social network. At the same time, the static link prediction methods ignored the evolving information of networks, it would reduce the prediction accuracy. Out of the above-mentioned situation, concerning the similarity index of the common neighbors and the similarity index of preference connections, a network dynamic link prediction method based on the hybrid simi- larity index was proposed. The method proposed a hybrid similarity index based on local information, assigned a influence attenuation factor for existed links into it to calculate, and predicted links according to the hybrid similarity index. The experiment results show that the above method can effectively improve the prediction precision.

关 键 词：社会网络 局部相似性指标 链路预测 网络局部信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]