论文标题
用于高效图表学习的地质图神经网络
Geodesic Graph Neural Network for Efficient Graph Representation Learning
论文作者
论文摘要
Graph神经网络（GNN）最近已应用于图形学习任务并实现了最新的结果（SOTA）结果。但是，许多竞争方法多次通过子图提取和定制标签运行GNNS，以捕获普通GNN很难学习的信息。此类操作是耗时的，并且不扩展到大图。在本文中，我们提出了一个称为Geodesic GNN（GDGNN）的有效GNN框架，该框架仅需要一个GNN运行，并在没有标记的情况下将节点之间的条件关系注入模型中。该策略有效地减少了子图方法的运行时。具体而言，我们将两个节点之间的最短路径视为周围邻里的空间图上下文。节点的GNN嵌入在最短路径上用于生成地球表示。 GDGNN以大地测量表示为条件，可以生成比普通GNN更丰富的结构信息的节点，链接和图形表示。从理论上讲，我们证明了GDGNN比普通的GNN更强大。我们提出了实验结果，以表明GDGNN通过SOTA GNN模型在各种图表学习任务上实现了高度竞争性的性能，同时花费大量时间。
Graph Neural Networks (GNNs) have recently been applied to graph learning tasks and achieved state-of-the-art (SOTA) results. However, many competitive methods run GNNs multiple times with subgraph extraction and customized labeling to capture information that is hard for normal GNNs to learn. Such operations are time-consuming and do not scale to large graphs. In this paper, we propose an efficient GNN framework called Geodesic GNN (GDGNN) that requires only one GNN run and injects conditional relationships between nodes into the model without labeling. This strategy effectively reduces the runtime of subgraph methods. Specifically, we view the shortest paths between two nodes as the spatial graph context of the neighborhood around them. The GNN embeddings of nodes on the shortest paths are used to generate geodesic representations. Conditioned on the geodesic representations, GDGNN can generate node, link, and graph representations that carry much richer structural information than plain GNNs. We theoretically prove that GDGNN is more powerful than plain GNNs. We present experimental results to show that GDGNN achieves highly competitive performance with SOTA GNN models on various graph learning tasks while taking significantly less time.
