Benefiting from the message passing mechanism, Graph Neural Networks (GNNs) have been successful on flourish tasks over graph data. However, recent studies have shown that attackers can catastrophically degrade the performance of GNNs by maliciously modifying the graph structure. A straightforward solution to remedy this issue is to model the edge weights by learning a metric function between pairwise representations of two end nodes, which attempts to assign low weights to adversarial edges. The existing methods use either raw features or representations learned by supervised GNNs to model the edge weights. However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e.g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph. We need representations that carry both feature information and as mush correct structure information as possible and are insensitive to structural perturbations. To this end, we propose an unsupervised pipeline, named STABLE, to optimize the graph structure. Finally, we input the well-refined graph into a downstream classifier. For this part, we design an advanced GCN that significantly enhances the robustness of vanilla GCN without increasing the time complexity. Extensive experiments on four real-world graph benchmarks demonstrate that STABLE outperforms the state-of-the-art methods and successfully defends against various attacks.

翻译：受益于消息传递机制，图神经网络在处理图数据的各类任务中取得了成功。然而，近期研究表明，攻击者可通过恶意修改图结构严重降低GNN的性能。解决该问题的一种直接方法是学习两个端节点配对表示之间的度量函数来建模边权重，从而试图为对抗性边分配较低的权重。现有方法要么使用原始特征，要么使用监督GNN学习到的表示来建模边权重。然而，这两种策略都面临一些直接问题：原始特征无法表征节点的多种属性（例如结构信息），而监督GNN学习到的表示可能因分类器在中毒图上的表现不佳而受到影响。我们需要同时携带特征信息与尽可能多的正确结构信息、且对结构扰动不敏感的表示。为此，我们提出一种名为STABLE的无监督流水线来优化图结构。最后，我们将精炼后的图输入下游分类器。针对该部分，我们设计了一种先进GCN，在不增加时间复杂度的前提下显著增强了标准GCN的鲁棒性。在四个真实图基准上的大量实验表明，STABLE优于现有最先进方法，并能成功防御多种攻击。