针对图数据分布偏移问题，提出对比学习增强方法提升模型泛化能力。
Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
- 利用对比学习挖掘潜在空间信息，生成对抗性增强数据
- 在多个公开OOD图数据集上表现优于现有基线方法
- 适合处理结构复杂的真实图数据分布偏移场景
协变量分布偏移指测试集中存在而训练集中缺失的某些结构特征，是真实世界复杂图数据中常见的分布外（OOD）问题。现有研究发现，大多数现成图神经网络（GNNs）无法应对此类偏移。此外，现有缓解方法往往未能充分利用潜在空间中的丰富信息。为此，我们提出MPAIACL——一种基于对比学习的更强大对抗性不变增强方法。该方法通过对比学习激发向量表示的内在信息潜力。大量实验表明，MPAIACL在多个公开的OOD图数据集上展现出出色的泛化能力和有效性，显著优于其他基线方法。代码已公开于https://github.com/flzeng1/MPAIACL。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。