Graph neural networks (GNNs) have become effective learning techniques for many downstream network mining tasks including node and graph classification, link prediction, and network reconstruction. However, most GNN methods have been developed for homogeneous networks with only a single type of node and edge. In this work we present muxGNN, a multiplex graph neural network for heterogeneous graphs. To model heterogeneity, we represent graphs as multiplex networks consisting of a set of relation layer graphs and a coupling graph that links node instantiations across multiple relations. We parameterize relation-specific representations of nodes and design a novel coupling attention mechanism that models the importance of multi-relational contexts for different types of nodes and edges in heterogeneous graphs. We further develop two complementary coupling structures: node invariant coupling suitable for node- and graph-level tasks, and node equivariant coupling suitable for link-level tasks. Extensive experiments conducted on six real-world datasets for link prediction in both transductive and inductive contexts and graph classification demonstrate the superior performance of muxGNN over state-of-the-art heterogeneous GNNs. In addition, we show that muxGNN's coupling attention discovers interpretable connections between different relations in heterogeneous networks.

中文翻译：

---

用于纵向膝骨关节炎预测的对抗性进化神经网络


图神经网络（GNN）已成为许多下游网络挖掘任务的有效学习技术，包括节点和图分类、链路预测和网络重建。然而，大多数 GNN 方法都是针对仅具有单一类型节点和边的同质网络而开发的。在这项工作中，我们提出了 muxGNN，一种用于异构图的多重图神经网络。为了对异构性进行建模，我们将图表示为由一组关系层图和一个跨多个关系链接节点实例的耦合图组成的多重网络。我们参数化节点的关系特定表示，并设计一种新颖的耦合注意机制，该机制可以对异构图中不同类型的节点和边的多关系上下文的重要性进行建模。我们进一步开发了两种互补的耦合结构：适用于节点和图级任务的节点不变耦合，以及适用于链路级任务的节点等变耦合。在六个真实世界数据集上进行了大量实验，用于传导和归纳上下文中的链接预测以及图分类，证明了 muxGNN 相对于最先进的异构 GNN 的优越性能。此外，我们还表明 muxGNN 的耦合注意力发现了异构网络中不同关系之间的可解释联系。