论文标题
啤酒花关系感知图形神经网络
Hop-Hop Relation-aware Graph Neural Networks
论文作者
论文摘要
图神经网络（GNN）广泛用于图表学习。但是，大多数GNN方法都是为均质或异质图设计的。在本文中，我们提出了一个新的模型，Hop-Hop关系感知的图形神经网络（HHR-GNN），以统一这两种类型的图形的表示。 HHR-GNN通过利用知识图嵌入来了解每个节点的个性化接收场，以学习不同啤酒花的中央节点表示之间的关系分数。在邻里聚合中，我们的模型同时允许进行霍普了解的投影和聚合。这种机制使中央节点能够学习一个可以应用于均匀和异质图的旋转邻域混合。五个基准测试的实验结果表明，与最先进的GNN相比，我们模型的竞争性能，例如，在大型异质图上，每个训练时期的时间成本更快，高达13k。
Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs. HHR-GNN learns a personalized receptive field for each node by leveraging knowledge graph embedding to learn relation scores between the central node's representations at different hops. In neighborhood aggregation, our model simultaneously allows for hop-aware projection and aggregation. This mechanism enables the central node to learn a hop-wise neighborhood mixing that can be applied to both homogeneous and heterogeneous graphs. Experimental results on five benchmarks show the competitive performance of our model compared to state-of-the-art GNNs, e.g., up to 13K faster in terms of time cost per training epoch on large heterogeneous graphs.
