Graph contrastive learning (GCL), learning the node representation by contrasting two augmented graphs in a self-supervised way, has attracted considerable attention. GCL is usually believed to learn the invariant representation. However, does this understanding always hold in practice? In this paper, we first study GCL from the perspective of causality. By analyzing GCL with the structural causal model (SCM), we discover that traditional GCL may not well learn the invariant representations due to the non-causal information contained in the graph. How can we fix it and encourage the current GCL to learn better invariant representations? The SCM offers two requirements and motives us to propose a novel GCL method. Particularly, we introduce the spectral graph augmentation to simulate the intervention upon non-causal factors. Then we design the invariance objective and independence objective to better capture the causal factors. Specifically, (i) the invariance objective encourages the encoder to capture the invariant information contained in causal variables, and (ii) the independence objective aims to reduce the influence of confounders on the causal variables. Experimental results demonstrate the effectiveness of our approach on node classification tasks.

翻译：图对比学习（GCL）通过以自监督方式对比两个增强图来学习节点表示，已引起广泛关注。通常认为GCL能够学习不变性表示。然而，这种理解在实践中是否始终成立？本文首次从因果视角研究GCL。通过利用结构因果模型（SCM）分析GCL，我们发现传统GCL可能因图中包含的非因果信息而无法充分学习不变性表示。如何改进并促使当前GCL学习更优的不变性表示？SCM提供了两个要求，启发我们提出一种新型GCL方法。具体而言，我们引入谱图增强来模拟对非因果因素的干预，并设计不变性目标和独立性目标以更好地捕捉因果因素。（i）不变性目标促使编码器捕获因果变量中的不变性信息，（ii）独立性目标旨在减少混杂因素对因果变量的影响。实验结果表明，我们的方法在节点分类任务上具有有效性。