高级检索

    基于图卷积的异质网络节点分类方法

    Heterogeneous Network Node Classification Method Based on Graph Convolution

    • 摘要: 图神经网络能够有效学习网络语义信息,在节点分类任务上取得了良好的效果.但仍面临挑战:如何充分利用异质网络丰富语义信息和全面结构信息使节点分类更精准.针对上述问题,提出了一种基于图卷积的异质网络节点分类框架(heterogeneous network node classification framework, HNNCF),包括异质网络约简和图卷积节点分类,解决异质网络节点分类问题.通过设计转换规则约简异质网络,将异质网络化简为语义化同质网络,利用节点间的关系表示保留异质网络多语义信息,降低网络结构建模复杂度;基于消息传递框架设计图卷积节点分类方法,在语义化同质网络上学习无1-sum约束的邻居权重等网络结构信息,深入挖掘关系语义特征,发现不同连接关系和邻居语义提取的差异性,生成节点的异质语义表示用于节点分类,识别节点类别标签.在3个公开的节点分类数据集上进行了实验,结果表明HNNCF能够充分利用异质网络多种语义信息,有效学习邻居节点权重等网络结构信息,提升节点分类效果.

       

      Abstract: Graph neural networks can effectively learn network semantic information and have achieved good performance on node classification tasks, but still facing challenge: how to make the best of rich heterogeneous semantic information and comprehensive structural information to make node classification more accurate. To resolve the above challenge, based on the graph convolution operation, HNNCF (heterogeneous network node classification framework) is proposed to solve the node classification task in heterogeneous networks, including two steps of heterogeneous network reduction and graph convolution node classification. Firstly, through the designed heterogeneous network reduction rules, HNNCF simplifies a heterogeneous network into a semantic homogeneous network and retains semantic information of the heterogeneous network through relation representations between nodes, reducing the complexity of network structure modeling. Then, based on the message passing framework, a graph convolution node classification method is designed to learn network structure information on the semantic homogeneous network, such as neighbor weights without 1-sum constraint, to discover the differences of relations and neighbor semantic extraction. Finally, heterogeneous node representations are generated and used to classify nodes to identify node category labels. Experiments on three public node classification datasets show that HNNCF can make the best of heterogeneous semantic information and effectively learn network structure information such as reasonable neighbor weights to improve the performance of heterogeneous network node classification.

       

    /

    返回文章
    返回