Self-Guided Robust Graph Structure Refinement
This work addresses the problem of defending GNNs against adversarial attacks in real-world scenarios where existing methods have limited applicability due to narrow assumptions.
The paper tackles the vulnerability of Graph Neural Networks (GNNs) to adversarial attacks by proposing a self-guided robust graph structure refinement framework that uses a clean sub-graph from the attacked graph itself, achieving effectiveness across various attack scenarios including non-targeted, targeted, feature attacks, e-commerce fraud, and noisy labels.
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.