一种新的链接预测方法在复杂网络中的应用

A Novel Link Prediction in Complex Networks

作为复杂网络分析的一项重要任务,链接预测已经被应用到诸多领域,例如:个性化推荐、决策支持系统和犯罪调查等。常用的链接预测方法主要是基于网络拓扑结构的方法,没有考虑网络的聚类信息因素。实际上,网络的聚类结果包含了对链接预测很重要的信息。在此基础上,一种基于聚类信息和网络特征的链接预测模型被提出,并在人造和真实网络数据集上进行了验证,具有较好的预测效果。

Link prediction is an important task of complex network analysis, which has been applied in various domains such as personal recommendation systems, decision support systems, crime investigation and so on. The classical link prediction methods are based on network topology structure and its features, in which the clustering information has not been considered. However, the clustering results of a network contain some vital information for link prediction. In this paper, a novel link prediction based on network clustering information and its features is proposed. Through experiments on the synthetic datasets and real world datasets, our proposed method has the good prediction accuracy.