arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.01332cs.LGcs.SIstat.ML
收藏

异构图Transformer

Heterogeneous Graph Transformer

University of California, Los Angeles(加州大学洛杉矶分校);Microsoft Research(微软研究院)

Ziniu Hu, Yuxiao Dong, Kuansan Wang, Yizhou Sun

摘要:

近年来,图神经网络(GNNs)在结构化数据建模方面取得了巨大的成功。然而,大多数GNN都是为同构图设计的,其中所有节点和边都属于相同的类型,这使得它们无法表示异构结构。在本文中,我们提出了异构图Transformer(HGT)的架构建模Web规模的异构图。为了对异质性进行建模,我们设计了节点和边缘类型相关的参数来表征每个边缘上的异质注意力,使HGT能够为不同类型的节点和边缘保持专用的表示。为了处理动态异构图,我们将相对时间编码技术引入到HGT中,它能够捕获具有任意持续时间的动态结构依赖。为了处理Web规模的图数据,我们设计了异构小批量图采样算法--HGSampling--以实现高效和可扩展的训练。在1.79亿个节点和20亿条边的Open Academic Graph上进行的大量实验表明,所提出的HGT模型在各种下游任务上的性能始终优于所有最先进的GNN基线9%-21%。

英文摘要:

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm---HGSampling---for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%--21% on various downstream tasks.

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。

↑