基于高阶关系的异构图学习
Learning on heterogeneous graphs using high-order relations
摘要：
异构图由不同的顶点和边类型组成。对异构图的学习通常使用元路径来处理异构性，方法是将图简化为同质网络、引导随机游动或捕获语义。然而，这些方法对元路径的选择敏感，次优路径导致性能差。在本文中，我们提出了一种方法学习异构图，而不使用元路径。具体来说，我们将异构图分解为不同的同构关系型图，然后将其组合以创建更高阶的关系型表示。这些表示保留了边缘的异质性，并保留了它们的边缘方向，同时捕获了不同顶点类型之间的相互作用。然后，这是补充注意力机制，以区分关系类型的邻居和关系类型本身的重要性。实验表明，我们的模型通常优于其他国家的最先进的基线在顶点分类任务上的三个常用研究的异构图形数据集。
英文摘要：
A heterogeneous graph consists of different vertices and edges types. Learning on heterogeneous graphs typically employs meta-paths to deal with the heterogeneity by reducing the graph to a homogeneous network, guide random walks or capture semantics. These methods are however sensitive to the choice of meta-paths, with suboptimal paths leading to poor performance. In this paper, we propose an approach for learning on heterogeneous graphs without using meta-paths. Specifically, we decompose a heterogeneous graph into different homogeneous relation-type graphs, which are then combined to create higher-order relation-type representations. These representations preserve the heterogeneity of edges and retain their edge directions while capturing the interaction of different vertex types multiple hops apart. This is then complemented with attention mechanisms to distinguish the importance of the relation-type based neighbors and the relation-types themselves. Experiments demonstrate that our model generally outperforms other state-of-the-art baselines in the vertex classification task on three commonly studied heterogeneous graph datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
