国家自然科学基金(62102321); 中央高校基本科研专项基金(D5000230095); 国家重点研发计划(2020AAA0108504)
异构图是一种具有多种类型节点或边的图, 也称异构信息网络, 其常被用来建模现实世界中具有丰富特征和关联模式的系统. 异构节点间的链接预测是网络分析领域的一个基本任务. 近年来, 异构图神经网络技术的发展极大地促进了链接预测任务的进步, 其通常将此任务当作节点间的特征相似性分析或基于成对节点特征的二分类问题. 然而, 现有的异构图神经网络技术在进行节点特征表示学习时, 往往仅关注相邻节点间的关联或基于元路径的结构信息. 这使得其不仅难以捕捉异构图中固有的环结构所蕴含的语义信息, 也忽视了不同层次的结构信息之间的互补性. 为解决上述问题, 设计一种基于多层次图结构的级联图卷积网络CGCN-MGS, 其由基于邻居、元路径和环3种不同层次图结构的图神经网络组成, 能从多层次特征中挖掘出丰富、互补的信息, 提高所学节点特征对节点语义和结构信息的表征能力. 多个基准数据集上的实验结果表明, CGCN-MGS在异构图的链接预测任务上能够取得目前最优的性能结果.
A heterogeneous graph is a graph with multiple types of nodes and edges, also known as a heterogeneous information network, which is often used to model systems with rich features and association patterns in the real world. Link prediction between heterogeneous nodes is a fundamental task in network analysis. In recent years, the development of heterogeneous graph neural network (HGNN) has greatly advanced the task of link prediction, which is usually regarded as a feature similarity analysis between nodes or a binary classification problem based on paired node features. However, when learning node feature representations, existing HGNNs usually only focus on the associations between adjacent nodes or the meta-path-based structural information. This not only makes these HGNNs difficult to capture the semantic information of the ring structure inherent in heterogeneous graphs but also ignores the complementarity of structural information at different levels. To solve the above issues, this study proposes a cascade graph convolution network based on multi-level graph structures (CGCN-MGS), which is composed of graph neural networks based on three graph structures of different levels: neighboring, meta-path, and ring structures. CGCN-MGS can mine rich and complementary information from multi-level features and improve the representation ability of the learned node features on the semantics and structure information of nodes. Experimental results on several benchmark datasets show that CGCN-MGS can achieve state-of-the-art performance on the link prediction of heterogeneous graphs.