Heterogeneous Graph Tree Networks

TL;DR

This paper introduces two novel heterogeneous graph neural network models, HetGTCN and HetGTAN, which effectively capture high-order neighborhood information without relying on meta-paths, outperforming existing methods in semi-supervised node classification.

Contribution

The paper presents two deep, meta-path-free heterogeneous graph neural network models that improve high-order neighborhood learning and outperform state-of-the-art baselines.

Findings

Outperform all state-of-the-art HGNN baselines on semi-supervised node classification.

Models can be deep without performance degradation.

Efficiently encode heterogeneity without meta-paths.

Abstract

Heterogeneous graph neural networks (HGNNs) have attracted increasing research interest in recent three years. Most existing HGNNs fall into two classes. One class is meta-path-based HGNNs which either require domain knowledge to handcraft meta-paths or consume huge amount of time and memory to automatically construct meta-paths. The other class does not rely on meta-path construction. It takes homogeneous convolutional graph neural networks (Conv-GNNs) as backbones and extend them to heterogeneous graphs by introducing node-type- and edge-type-dependent parameters. Regardless of the meta-path dependency, most existing HGNNs employ shallow Conv-GNNs such as GCN and GAT to aggregate neighborhood information, and may have limited capability to capture information from high-order neighborhood. In this work, we propose two heterogeneous graph tree network models: Heterogeneous Graph Tree Convolutional Network (HetGTCN) and Heterogeneous Graph Tree Attention Network (HetGTAN), which do not rely on meta-paths to encode heterogeneity in both node features and graph structure. Extensive experiments on three real-world heterogeneous graph data demonstrate that the proposed HetGTCN and HetGTAN are efficient and consistently outperform all state-of-the-art HGNN baselines on semi-supervised node classification tasks, and can go deep without compromising performance.