Recent studies have revealed that GNNs are vulnerable to adversarial attacks. To defend against such attacks, robust graph structure refinement (GSR) methods aim at minimizing the effect of adversarial edges based on node features, graph structure, or external information. However, we have discovered that existing GSR methods are limited by narrowassumptions, such as assuming clean node features, moderate structural attacks, and the availability of external clean graphs, resulting in the restricted applicability in real-world scenarios. In this paper, we propose a self-guided GSR framework (SG-GSR), which utilizes a clean sub-graph found within the given attacked graph itself. Furthermore, we propose a novel graph augmentation and a group-training strategy to handle the two technical challenges in the clean sub-graph extraction: 1) loss of structural information, and 2) imbalanced node degree distribution. Extensive experiments demonstrate the effectiveness of SG-GSR under various scenarios including non-targeted attacks, targeted attacks, feature attacks, e-commerce fraud, and noisy node labels. Our code is available at https://github.com/yeonjun-in/torch-SG-GSR.

翻译：近期研究表明，图神经网络易受对抗攻击威胁。为抵御此类攻击，鲁棒图结构优化方法旨在基于节点特征、图结构或外部信息最小化对抗边的影响。然而我们发现，现有图结构优化方法受限于狭窄假设（如假设节点特征纯净、结构攻击强度适中、存在外部纯净图等），导致其在真实场景中的适用性受限。本文提出自引导图结构优化框架（SG-GSR），该框架利用给定受攻击图自身发现的纯净子图。我们进一步提出新型图增强与分组训练策略，以应对纯净子图提取中的两个技术挑战：1）结构信息丢失，2）节点度分布不平衡。大量实验表明，SG-GSR在非目标攻击、目标攻击、特征攻击、电商欺诈及带噪节点标签等多种场景下均具有有效性。代码已开源：https://github.com/yeonjun-in/torch-SG-GSR。