In this article, to capture higher-order structural information of the heterogeneous graphs, we proposed AHGCL which introduces a novel data augmentation method by calculating cosine similarity of the feature vectors generated by a network embedding method. A dual-level contrastive loss function is provided to maximize common information among similar instances from two various perspectives including the node embeddings at the original graph and augmentation graph views. Experimental results on four real-world datasets illustrate that the proposed AHGCL model outperforms state-of-the-art graph representation learning approaches for node classification tasks.

Heterogeneous graph neural networks (HGNNs) have demonstrated promising capabilities in addressing various problems defined on heterogeneous graphs containing multiple types of nodes or edges. However, traditional HGNN models depend on label information and capture the local structural information of the original graph. In this article, we propose a novel heterogeneous graph contrastive learning method with augmentation graph (AHGCL). Specifically, we construct an augmentation graph by calculating the feature similarity of nodes to capture latent structural information. For the original graph and the augmentation graph, we employ a shared graph neural network (GNN) encoder to extract the semantic features of nodes with different meta-paths. The feature information is aggregated through a semantic-level attention mechanism to generate final node embeddings, which capture latent high-order semantic structural information. Considering the problems of label information for the real-world d...