Learning Robust Representation through Graph Adversarial Contrastive Learning
arXiv:2201.13025 · doi:10.1007/978-3-031-00123-9_54
Abstract
Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features. Thus, it is requisite to learn robust representations in graph neural networks. To improve the robustness of graph representation learning, we propose a novel Graph Adversarial Contrastive Learning framework (GraphACL) by introducing adversarial augmentations into graph self-supervised learning. In this framework, we maximize the mutual information between local and global representations of a perturbed graph and its adversarial augmentations, where the adversarial graphs can be generated in either supervised or unsupervised approaches. Based on the Information Bottleneck Principle, we theoretically prove that our method could obtain a much tighter bound, thus improving the robustness of graph representation learning. Empirically, we evaluate several methods on a range of node classification benchmarks and the results demonstrate GraphACL could achieve comparable accuracy over previous supervised methods.
References in corpus (16)
- DeepWalk: Online Learning of Social Representations
- A Simple Framework for Contrastive Learning of Visual Representations
- The information bottleneck method
- Adversarial Attacks on Neural Networks for Graph Data
- Graph Contrastive Learning with Augmentations
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
- Deep Graph Contrastive Representation Learning
- Contrastive Multi-View Representation Learning on Graphs
- Adversarial Attacks on Graph Neural Networks via Meta Learning
- Transferring Robustness for Graph Neural Network Against Poisoning Attacks
- Diffusion Improves Graph Learning
- Graph Information Bottleneck
- Deep Graph Infomax
- GraphDefense: Towards Robust Graph Convolutional Networks
- Adversarial Defense Framework for Graph Neural Network
- Can Adversarial Network Attack be Defended?