Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
This addresses a common out-of-distribution problem in graph neural networks for real-world applications, but it appears incremental as it builds on existing methods to better leverage latent space information.
The paper tackles the problem of covariate distribution shift in graph data, where test sets have structural features absent from training, by introducing MPAIACL, a method using contrastive learning for adversarial invariant augmentation, which demonstrates robust generalization and effectiveness compared to baselines on various OOD datasets.
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.