Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs

In recent years, methods based on heterogeneous graph neural networks (HGNNs) have been widely used for embedding heterogeneous graphs (HGs) due to their ability to effectively encode the rich information from HGs into low-dimensional node embeddings. Existing HGNNs focus on neighbor aggregation and semantic fusion while neglecting the HG structure and learning paradigms. However, the original data in the HG might lack node features, which may not be effectively accounted for by existing models. Additionally, exclusively relying on a single supervised learning approach may only partially leverage the invariant information in graph data. To address these challenges, we introduce the Contrastive Auxiliary Learning Model for Heterogeneous Graphs (CALHG), which combines edge perturbation and graph diffusion to enhance graph data, allowing it to capture the inherent structural information within heterogeneous graphs fully. Additionally, we employ a category-guided multi-view contrastive learning optimizing strategy, which does not rely on positive and negative samples for model training, enabling us to capture the intrinsic invariances in heterogeneous graph data. Extensive experiments and analyses on five benchmark datasets without node features and three benchmark datasets with node features validate the effectiveness and efficiency of our novel method compared with several state-of-the-art methods.