Heterogeneous Graph Transformer

TL;DR

The paper introduces Heterogeneous Graph Transformer (HGT), a novel GNN architecture designed for modeling large-scale, dynamic, heterogeneous graphs with improved performance over existing methods.

Contribution

HGT incorporates node- and edge-type dependent parameters and a relative temporal encoding to effectively model heterogeneity and dynamics in large-scale graphs.

Findings

HGT outperforms state-of-the-art GNNs by 9%-21% on various tasks.

HGT effectively models Web-scale heterogeneous and dynamic graphs.

The proposed HGSampling enables scalable training on large graphs.

Abstract

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.