Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Fanlong, Gan, Wensheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911609928024064
author Zeng, Fanlong
Gan, Wensheng
author_facet Zeng, Fanlong
Gan, Wensheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00716
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
Zeng, Fanlong
Gan, Wensheng
Machine Learning
Artificial Intelligence
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.
title Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.00716