arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.02636cs.LG
收藏

用于高效图表示学习的测地图神经网络

Geodesic Graph Neural Network for Efficient Graph Representation Learning

Washington University in St. Louis(圣路易斯华盛顿大学);Peking University(北京大学)

Lecheng Kong, Yixin Chen, Muhan Zhang

摘要:

图神经网络(GNN)最近已被应用于图学习任务,并取得了最先进的(SOTA)结果。然而,许多有竞争力的方法通过子图提取和自定义标记多次运行GNN,以捕获普通GNN难以学习的信息。这样的操作是耗时的,并且不能扩展到大型图。在本文中,我们提出了一个高效的GNN框架,称为Geodesic GNN(GDGNN),它只需要运行一次GNN,并将节点之间的条件关系注入到模型中,而无需标记。该策略有效地减少了子图方法的运行时间。具体来说,我们将两个节点之间的最短路径视为它们周围邻域的空间图上下文。最短路径上节点的GNN嵌入用于生成测地线表示。在测地线表示的条件下,GDGNN可以生成节点,链接和图形表示,这些表示比普通GNN携带更丰富的结构信息。我们从理论上证明了GDGNN比普通GNN更强大。我们目前的实验结果表明,GDGNN在各种图学习任务上与SOTA GNN模型相比具有很强的竞争力,同时花费的时间明显更少。

英文摘要:

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.

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。

↑