Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: $i)$ for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption; $ii)$ surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node.

翻译：许多研究表明，图神经网络（GNN）对图结构的小规模扰动——通常称为对抗性变化——在节点级预测上并不鲁棒。然而，由于图的目视检查较为困难，目前尚不清楚所研究的扰动是否始终满足对抗样本的一个核心假设：语义内容保持不变。为解决这一问题，我们引入了一种更具原则性的对抗图概念，该概念能够感知语义内容的变化。通过上下文随机块模型（CSBMs）和真实世界图上的实验，我们的结果揭示了：$i)$ 对于大多数节点，常见的扰动模型包含大量违反语义不变假设的扰动图；$ii)$ 令人惊讶的是，所有被评估的GNN均表现出过度鲁棒性——即超出语义变化点的鲁棒性。我们发现这是对抗样本的一种互补现象，并表明将训练图的标签结构纳入GNN的推理过程可显著降低过度鲁棒性，同时对测试准确率和对抗鲁棒性产生积极影响。理论上，利用我们基于语义感知的鲁棒性新概念，我们证明了对于归纳式分类新添加的节点，鲁棒性与准确性之间不存在权衡。