paper-with-me

홈 › Papers

Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

2025-11-30 · Fanlong Zeng, Wensheng Gan arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.00716

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData Augmentation

Similar Papers 제목 키워드 기반

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

2022-11-05 · NeurIPS 2023 11 · Yongduo Sui, Qitian Wu, Jiancan Wu, Qing Cui 외

The issue of distribution shifts is emerging as a critical concern in graph representation learning. From the perspective of invariant learning and stable learning, a recently well-established paradigm for out-of-distrib…

Data AugmentationGraph ClassificationGraph Representation LearningOut-of-Distribution Generalization+1

Mitigating Graph Covariate Shift via Score-based Out-of-distribution Augmentation

2024-10-23 · Bohan Wang, Yurui Chang, Lu Lin

Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of…

Graph GenerationGraph Learning

Generative Contrastive Graph Learning for Recommendation

2023-07-11 · Yonghui Yang, Zhengwei Wu, Le Wu, Kun Zhang 외

By treating users' interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering(CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning(…

Collaborative FilteringContrastive LearningData AugmentationGraph Learning+1

Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization

2026-04-09 · Simon Zhang, Ryan P. DeMilt, Kun Jin, Cathy H. Xia arxiv

Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice when training and testing data come from different environments. Covariate …

Representation LearningGraph Classification

Graph Contrastive Learning with Implicit Augmentations

2022-11-07 · Huidong Liang, Xingjian Du, Bilei Zhu, Zejun Ma 외

Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e.g., randomly adding or dropping edges and nodes). Nevertheless, altering certain edges or nodes can unexpectedl…

Contrastive LearningGraph ClassificationNode Classification