Feng Shengyu, Jing Baoyu, Zhu Yada, Tong Hanghang
Carnegie Mellon University, USA.
University of Illinois at Urbana-Champaign, USA.
ACM Trans Knowl Discov Data. 2023 Dec;18(4):1-22. doi: 10.1145/3638054.
Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle. Recently, the data-augmentation-based contrastive learning method has advanced to show great power in the visual domain, and some works extended this method from images to graphs. However, unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which leaves much space for improvement. In this work, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, (ArieL), to extract informative contrastive samples within reasonable constraints. We develop a new technique called information regularization for stable training and use subgraph sampling for scalability. We generalize our method from node-level contrastive learning to the graph level by treating each graph instance as a super-node. ArieL consistently outperforms the current graph contrastive learning methods for both node-level and graph-level classification tasks on real-world datasets. We further demonstrate that ArieL is more robust in the face of adversarial attacks.
对比学习是图表示学习中一种有效的无监督方法，对比学习的关键在于正负样本的构建。以往的方法通常以图中节点的邻近性为原则。最近，基于数据增强的对比学习方法在视觉领域取得了进展，并显示出强大的能力，一些工作将该方法从图像扩展到了图。然而，与图像上的数据增强不同，图上的数据增强远没有那么直观，而且很难提供高质量的对比样本，这就留下了很大的改进空间。在这项工作中，通过引入用于数据增强的对抗性图视图，我们提出了一种简单而有效的方法（ArieL），以在合理的约束内提取信息丰富的对比样本。我们开发了一种名为信息正则化的新技术用于稳定训练，并使用子图采样来提高可扩展性。通过将每个图实例视为一个超级节点，我们将我们的方法从节点级对比学习推广到图级。在真实世界数据集上的节点级和图级分类任务中，ArieL始终优于当前的图对比学习方法。我们进一步证明，ArieL在面对对抗性攻击时更具鲁棒性。
