Heterogeneous Graph Attention Network

TLDR

Graph neural networks excel at graph representation, yet their application to heterogeneous graphs—containing diverse node and link types—remains underexplored due to challenges posed by heterogeneity and rich semantic information. This work introduces a heterogeneous graph neural network that employs hierarchical attention, combining node‑level and semantic‑level mechanisms. Node‑level attention learns the importance between a node and its meta‑path neighbors, while semantic‑level attention captures the relevance of different meta‑paths, and the two attentions jointly guide hierarchical aggregation of neighbor features to produce node embeddings. Experiments on three real‑world heterogeneous graphs demonstrate that the proposed model outperforms state‑of‑the‑art methods and offers interpretable graph analysis.

Abstract

Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions. Specifically, the node-level attention aims to learn the importance between a node and its meta-path based neighbors, while the semantic-level attention is able to learn the importance of different meta-paths. With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of our proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.