融合属性信息的异质网络嵌入方法  

Heterogeneous network embedding with attributes information fusion

作　　者：张贤坤[1] 袁菁 罗学雄 段双玉 Zhang Xiankun;Yuan Jing;Luo Xuexiong;Duan Shuangyu(College of Artificial Intelligence,Tianjin University of Science&Technology,Tianjin 300457,China;Dept.of Computing,Macquarie University,Sydney 2122,Australia;College of Information Technology Engineering,Tianjin University of Technology&Education,Tianjin 300350,China)

机构地区：[1]天津科技大学人工智能学院,天津300457 [2]麦考瑞大学计算机系,悉尼2122 [3]天津职业技术师范大学信息技术工程学院,天津300350

出　　处：《计算机应用研究》2022年第6期1767-1771,1778,共6页Application Research of Computers

基　　金：天津市自然科学基金资助项目(19JCYBJC15300);天津市高等学校本科教学质量与教学改革研究计划项目(B201005706);教育部第二批新工科研究与实践项目(E-HJFZQG20202405)。

摘　　要：现有的异质网络嵌入方法不仅忽略了网络中的异质边及其对节点嵌入的不同影响,还未考虑到网络结构与节点属性的融合。为此提出了一种融合属性信息的异质网络嵌入方法(SHANE)。将序列到序列(seq2seq)模型应用到依据边类型划分的子图中,无缝融合节点的结构信息和属性信息,同时捕捉节点的高阶语义信息。实验表明,SHANE在两个不同类型的数据集中进行链接预测任务,可以取得相对显著的效果。The existing heterogeneous network embedding methods not only ignore heterogeneous edges in networks and their different effects on node embedding,but also do not consider the integration of network structure and node attributes.This paper proposed a novel heterogeneous network embedding method with attributes information fusion,which named SHANE.It applied the sequence to sequence(seq2seq)model to the sub-graphs divided according to edge types,seamlessly integrated the structure information and attributes information of nodes,and captured the high-order semantic information of nodes simultaneously.Experiments show that SHANE can achieve relatively significant results in link prediction tasks in two different types of datasets.

关 键 词：网络嵌入 异质网络 seq2seq 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]