A Unique Framework of Heterogeneous Augmentation Graph Contrastive Learning for Both Node and Graph Classification

Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: heterogeneous augmentation. Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.