SHGNN: Structure-Aware Heterogeneous Graph Neural Network

TL;DR

SHGNN introduces a structure-aware approach to heterogeneous graph embedding by integrating local structure and meta-path information, significantly improving node classification and clustering performance.

Contribution

The paper proposes a novel SHGNN model that effectively incorporates graph structure into heterogeneous graph embedding, addressing limitations of previous meta-path based methods.

Findings

Achieved state-of-the-art results on benchmark datasets.

Effectively captures local structure information.

Improves node classification and clustering accuracy.

Abstract

Many real-world graphs (networks) are heterogeneous with different types of nodes and edges. Heterogeneous graph embedding, aiming at learning the low-dimensional node representations of a heterogeneous graph, is vital for various downstream applications. Many meta-path based embedding methods have been proposed to learn the semantic information of heterogeneous graphs in recent years. However, most of the existing techniques overlook the graph structure information when learning the heterogeneous graph embeddings. This paper proposes a novel Structure-Aware Heterogeneous Graph Neural Network (SHGNN) to address the above limitations. In detail, we first utilize a feature propagation module to capture the local structure information of intermediate nodes in the meta-path. Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path. Finally, we leverage a meta-path aggregator to fuse the information aggregated from different meta-paths. We conducted experiments on node classification and clustering tasks and achieved state-of-the-art results on the benchmark datasets, which shows the effectiveness of our proposed method.