A Self-Supervised Heterogeneous Graph Attention Model Based on Adaptable Step-Size Metapaths

Graphs are widely used to model networks in real-world applications, with heterogeneous graph neural networks gaining increasing attention in recent years. Existing methods generally rely on first-order or high-order neighbors to capture semantic relationships, where metapath-based approaches are the most popular ones. However, existing metapath-based models not only require predefined metapaths based on prior knowledge, but also lack the consideration of metapath sequence modeling. Additionally, labeled data are scarce in massive graph data, and existing self-supervised or semisupervised models heavily rely on data enhancement strategies and complex frameworks. To address these limitations, we propose a self-supervised heterogeneous graph attention model (HGAM) based on adaptable step-size metapaths. Our model requires no prior knowledge to select the type of metapath and can adaptively capture the specific step-size metapath with high importance. The adaptable step-size metapaths module not only considers the attention weight in different step sizes, but also pays attention to the changing trend of attention, which expands the receptive field of the model and integrates global information preferably. To alleviate labeled data scarcity, our model employs a dual contrastive learning strategy. HGAM learns global representations by contrasting a high-order meta-graph against nodes, while preserving local structure through a cross-view comparison of first-order and high-order semantics. Extensive experiments on three different types of tasks, including node classification, clustering, and link prediction, are conducted on real-world datasets. Experimental results demonstrate that HGAM achieves superior performance compared to state-of-the-art methods.