Graph contrastive learning (GCL) has recently emerged as a promising approach for graph representation learning. Some existing methods adopt the 1-vs-K scheme to construct one positive and K negative samples for each graph, but it is difficult to set K. For those methods that do not use negative samples, it is often necessary to add additional strategies to avoid model collapse, which could only alleviate the problem to some extent. All these drawbacks will undoubtedly have an adverse impact on the generalizability and efficiency of the model. In this paper, to address these issues, we propose a novel graph self-contrast framework GraphSC, which only uses one positive and one negative sample, and chooses triplet loss as the objective. Specifically, self-contrast has two implications. First, GraphSC generates both positive and negative views of a graph sample from the graph itself via graph augmentation functions of various intensities, and use them for self-contrast. Second, GraphSC uses Hilbert-Schmidt Independence Criterion (HSIC) to factorize the representations into multiple factors and proposes a masked self-contrast mechanism to better separate positive and negative samples. Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample. Therefore, we explicitly reduced the absolute distance between the anchor and positive sample to accelerate convergence. Finally, we conduct extensive experiments to evaluate the performance of GraphSC against 19 other state-of-the-art methods in both unsupervised and transfer learning settings.

翻译：图对比学习（GCL）近年来已成为图表示学习领域一种颇具前景的方法。现有部分方法采用1-vs-K方案为每个图构造一个正样本和K个负样本，但K值的设定存在困难。对于不使用负样本的方法，通常需要添加额外策略以避免模型坍塌，而这仅能在一定程度上缓解问题。这些缺陷无疑会对模型的泛化能力和效率产生负面影响。为解决上述问题，本文提出一种新颖的图自对比框架GraphSC，该框架仅使用一个正样本和一个负样本，并采用三元组损失作为目标函数。具体而言，"自对比"包含两层含义：第一，GraphSC通过不同强度的图增强函数，从图样本自身生成其正视图和负视图，并用于自对比学习；第二，GraphSC利用希尔伯特-施密特独立性准则（HSIC）将表示分解为多个因子，并提出一种掩码自对比机制以更好地区分正负样本。此外，由于三元组损失仅优化锚点与正负样本间的相对距离，难以保证锚点与正样本间的绝对距离。为此，我们显式地缩小锚点与正样本间的绝对距离以加速收敛。最后，我们在无监督学习和迁移学习两种设置下开展了大量实验，将GraphSC与19种其他先进方法进行性能对比评估。