Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most out-of-the-box graph neural networks (GNNs) fail to account for covariate shifts. Furthermore, we observe that existing methods aimed at addressing covariate shifts often fail to fully leverage the rich information contained within the latent space. Motivated by the potential of the latent space, we introduce a new method called MPAIACL for More Powerful Adversarial Invariant Augmentation using Contrastive Learning. MPAIACL leverages contrastive learning to unlock the full potential of vector representations by harnessing their intrinsic information. Through extensive experiments, MPAIACL demonstrates its robust generalization and effectiveness, as it performs well compared with other baselines across various public OOD datasets. The code is publicly available at https://github.com/flzeng1/MPAIACL.

翻译：协变量分布偏移是指测试集中存在的某些结构特征在训练集中缺失的现象。这是分布外问题的一种常见类型，在具有复杂结构的真实世界图数据中频繁出现。现有研究表明，大多数现成的图神经网络未能有效处理协变量偏移。此外，我们观察到现有针对协变量偏移的方法往往无法充分利用潜在空间中的丰富信息。基于潜在空间的潜力，我们提出了一种名为MPAIACL的新方法，即通过对比学习实现更强大的对抗性不变增强。MPAIACL利用对比学习挖掘向量表示的内在信息，从而充分释放其潜力。通过大量实验，MPAIACL在多个公开的OOD数据集上均表现出优于其他基线方法的性能，证明了其强大的泛化能力和有效性。代码已公开于https://github.com/flzeng1/MPAIACL。