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.
翻译:多元图形由不同的脊椎和边缘类型组成。 在多元图形上学习通常使用元路径处理异质性, 将图形降为同质网络, 引导随机行走或捕捉语义。 然而, 这些方法对于选择元路径非常敏感, 其次优路径导致性能差。 在本文中, 我们建议一种方法, 在不使用元路径的情况下学习异质图形。 具体地说, 我们将一个异性图形分解成不同的同质关系类型图形, 然后将其组合起来, 以创建更高顺序的关系类型表示。 这些表达方式保存边缘的异质性, 并保留其边缘方向, 同时捕捉不同顶端类型多重跳的相互作用 。 然后辅之以关注机制, 以区分基于关系类型的邻居和关系类型本身的重要性 。 实验表明, 我们的模型通常在三个常用的相异式图形数据集的脊椎分类任务中, 超越其他状态的基线 。