Graph contrastive learning (GCL), as a self-supervised learning method, can solve the problem of annotated data scarcity. It mines explicit features in unannotated graphs to generate favorable graph representations for downstream tasks. Most existing GCL methods focus on the design of graph augmentation strategies and mutual information estimation operations. Graph augmentation produces augmented views by graph perturbations. These views preserve a locally similar structure and exploit explicit features. However, these methods have not considered the interaction existing in subgraphs. To explore the impact of substructure interactions on graph representations, we propose a novel framework called subgraph network-based contrastive learning (SGNCL). SGNCL applies a subgraph network generation strategy to produce augmented views. This strategy converts the original graph into an Edge-to-Node mapping network with both topological and attribute features. The single-shot augmented view is a first-order subgraph network that mines the interaction between nodes, node-edge, and edges. In addition, we also investigate the impact of the second-order subgraph augmentation on mining graph structure interactions, and further, propose a contrastive objective that fuses the first-order and second-order subgraph information. We compare SGNCL with classical and state-of-the-art graph contrastive learning methods on multiple benchmark datasets of different domains. Extensive experiments show that SGNCL achieves competitive or better performance (top three) on all datasets in unsupervised learning settings. Furthermore, SGNCL achieves the best average gain of 6.9\% in transfer learning compared to the best method. Finally, experiments also demonstrate that mining substructure interactions have positive implications for graph contrastive learning.

翻译：图对比学习（GCL）作为一种自监督学习方法，能够解决标注数据稀缺的问题。它通过挖掘无标注图中的显式特征，为下游任务生成有利的图表示。现有的大多数图对比学习方法侧重于图增强策略和互信息估计操作的设计。图增强通过图扰动产生增强视图，这些视图保留了局部相似结构并利用了显式特征。然而，这些方法并未考虑子图中存在的交互关系。为探究子结构交互对图表示的影响，我们提出了一种名为子图网络对比学习（SGNCL）的新框架。SGNCL采用子图网络生成策略来产生增强视图，该策略将原始图转换为同时包含拓扑和属性特征的边到节点映射网络。单次生成的增强视图是一阶子图网络，挖掘了节点与节点、节点与边以及边与边之间的交互。此外，我们还研究了二阶子图增强对挖掘图结构交互的影响，并进一步提出了融合一阶和二阶子图信息的对比目标函数。我们在多个不同领域的基准数据集上将SGNCL与经典及最先进的图对比学习方法进行了比较。大量实验表明，在无监督学习设置下，SGNCL在所有数据集上均取得了具有竞争力或更优的性能（前三名）。此外，在迁移学习中，相比最优方法，SGNCL获得了6.9%的最佳平均增益。最后，实验也证明挖掘子结构交互对图对比学习具有积极意义。