Exploring Multiple Hypergraphs for Heterogeneous Graph Neural Networks
Exploring Multiple Hypergraphs for Heterogeneous Graph Neural Networks
复制标题
DOI：
10.1016/j.eswa.2023.121230
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Y. Wang;Yingji Li;Yuehua Wu;Xin Wang
中科院分区：
文献类型：
--
作者：
Y. Wang;Yingji Li;Yuehua Wu;Xin Wang
图神经网络在学习同构网络的图表示方面表现出显着的能力。然而，现实世界的网络数据通常可以表示为具有不同类型的节点和边的异构网络，例如社交网络、流量网络和分子网络。网络异构性给网络分析和挖掘带来了巨大的挑战。基于模体的超图保持高阶邻近性并捕获复合语义交互。由于不是所有的节点和边在原始网络中总是存在于一个特定的超图，这是必要的，多个基于模体的超图被认为是增强网络表示。因此，我们提出了一个新的框架，探索基于多个Motif-basedHypergraphs的HeterogeneousGraphNeuralNetworks学习网络表示，命名为MoH-HGNN，它利用超图卷积和注意力操作来捕获复杂的连接模式。具体而言，我们进行了两个层次的注意力网络的层次结构，即超边级的注意力，学习不同类型的节点之间的重要性和全面的语义级的注意力，捕捉不同类型的模体结构的重要性。我们在四个真实世界的数据集上进行了广泛的实验，以验证我们提出的框架的有效性。
Graph neural networks have demonstrated significant power in learning graph representations for homogeneous networks. However, real-world network data can often be denoted by heterogeneous networks with different types of nodes and edges, such as social, traffic, and molecular networks. Network heterogeneity presents significant challenges for network analysis and mining. Motif-based hypergraphs preserve high-order proximity and capture composite semantic interactions. Because not all nodes and edges in the original network always exist in a specific hypergraph, it is essential that multiple motif-based hypergraphs are considered to enhance the network representation. Therefore, we propose a novel framework for exploringMultiple Motif-basedHypergraphs forHeterogeneousGraphNeuralNetworks to learn network representations, named MoH-HGNN, which leverages hypergraph convolution and attention operations to capture complex connectivity patterns. Specifically, we conducted two levels of attention networks with hierarchical structures, namely hyperedge-level attention to learn the importance among different types of nodes and comprehensive semantic-level attention to capture the importance of different types of motif structures. We extensively experimented on four real-world datasets to verify the effectiveness of our proposed framework.