Graph Transformer Networks

TL;DR

Graph Transformer Networks (GTNs) automatically generate and learn new graph structures to improve node representation, outperforming existing methods without relying on domain-specific preprocessing or meta-paths.

Contribution

GTNs introduce a novel end-to-end framework that learns to generate useful multi-hop graph connections, enhancing representation learning on heterogeneous and misspecified graphs.

Findings

GTNs outperform state-of-the-art methods on benchmark node classification tasks.

GTNs learn meaningful new graph structures without domain knowledge.

GTNs effectively generate multi-hop connections for improved node embeddings.

Abstract

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion. Graph Transformer layer, a core layer of GTNs, learns a soft selection of edge types and composite relations for generating useful multi-hop connections so-called meta-paths. Our experiments show that GTNs learn new graph structures, based on data and tasks without domain knowledge, and yield powerful node representation via convolution on the new graphs. Without domain-specific graph preprocessing, GTNs achieved the best performance in all three benchmark node classification tasks against the state-of-the-art methods that require pre-defined meta-paths from domain knowledge.