Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GCL) based methods specifically suffer from adversarial attacks due to their inherent design that highly depends on the self-supervision signals derived from the original graph, which however already contains noise when the graph is attacked. To achieve adversarial robustness against such attacks, existing methods adopt adversarial training (AT) to the GCL framework, which considers the attacked graph as an augmentation under the GCL framework. However, we find that existing adversarially trained GCL methods achieve robustness at the expense of not being able to preserve the node feature similarity. In this paper, we propose a similarity-preserving adversarial graph contrastive learning (SP-AGCL) framework that contrasts the clean graph with two auxiliary views of different properties (i.e., the node similarity-preserving view and the adversarial view). Extensive experiments demonstrate that SP-AGCL achieves a competitive performance on several downstream tasks, and shows its effectiveness in various scenarios, e.g., a network with adversarial attacks, noisy labels, and heterophilous neighbors. Our code is available at https://github.com/yeonjun-in/torch-SP-AGCL.

翻译：近期研究表明，图神经网络（GNN）模型易受对抗性攻击，这类攻击通过对图结构和节点特征施加难以察觉的扰动而实现。在各类GNN模型中，基于图对比学习（GCL）的方法尤其易受对抗性攻击影响，因其固有设计高度依赖从原始图中导出的自监督信号——然而当图遭受攻击时，该信号本身已包含噪声。为抵御此类攻击实现对抗鲁棒性，现有方法将对抗训练（AT）引入GCL框架，将被攻击图视为GCL框架下的一种数据增强方式。然而我们发现，现有采用对抗训练的GCL方法在获得鲁棒性的同时，牺牲了对节点特征相似性的保留能力。本文提出保留相似性的对抗性图对比学习（SP-AGCL）框架，该框架利用两种具有不同性质的辅助视图（即节点相似性保留视图与对抗性视图）与干净图进行对比学习。大量实验表明，SP-AGCL在多项下游任务中取得具有竞争力的性能，并在多种场景下（如存在对抗性攻击、噪声标签及异质邻居的网络）展现出有效性。我们的代码开源在 https://github.com/yeonjun-in/torch-SP-AGCL。