【摘要】 真实世界中不同类型的对象之间相互连接,形成异质信息网络.预测网络中对象之间的连接或交互是网络分析中的一个重要任务.不同于传统的同质性网络的链路预测,异质信息网络中,由于存在多种类型的节点和边,节点之间可以通过不同的关系进行连接.文中使用元路径,即通过一组关系连接了多种节点类型的路径,来描述异质信息网络中不同类型对象之间各种连接的不同语义,从而提出一种异质信息网络链路预测模型,通过组合对象之间在不同元路径上建立连接的概率来进行链路预测.在DBLP和Last.fm两个真实数据集上的实验结果表明:在7种关系的链路预测中,相比最好的基准方法,文中方法的AUC值平均提升了5.93%;另外,在链路预测中,通过元路径区分不同类型的节点和边之后,预测精度得到了明显提升;最后,为了平衡预测精度和模型的可扩展性,实验分析表明链路预测中仅考虑路径长度小于5的元路径就已经足够产生很好的预测结果.更多还原

【Abstract】 Real-world,multiple-typed objects are often interconnected,forming heterogeneous information networks.The problem of predicting links or interactions between objects in a network is an important task of network analysis.Different from traditional link prediction tasks in homogeneous networks,heterogeneous information networks have multiple distinct types of interrelated objects and relationships,and the objects in heterogeneous networks can be connected via different relationships.In this paper,we use meta-path,a kind of path that connects object types via a sequence of relations,to describe distinct semantics of different types of nodes and relationships,and propose a meta path-based link prediction model for heterogeneous information networks(MPLP).In this model we perform link prediction by combining the link probabilities between nodes on different meta-paths.The method is evaluated with two different genres of datasets:DBLP and Last.fm.Experimental results show that when predicting the formation of seven types of relationships,the AUC value of our method is on average improved 5.93%compared with the most accurate method.Furthermore,distinguishing different types of nodes and relationships by using meta-paths can improve the prediction accuracy significantly.At last, in order to balance the prediction accuracy and the scalability of our model,an experimental analysis demonstrates that considering meta-paths whose lengths are less than 5is enough to produce good results in terms of link prediction.更多还原