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 ass
通过对来自不同神经流的图神经网络的研究,着重探讨与 BIBO 稳定性、Lyapunov 稳定性、结构稳定性和保守稳定性等各种稳定性概念的联系。通过启发于物理原理,我们主张采用保守 Hamilton 神经流构建对抗攻击具有鲁棒性的图神经网络。在多个基准数据集上,我们对不同神经流的图神经网络的对抗鲁棒性进行了经验比较,结果表明采用具有 Lyapunov 稳定性的保守 Hamilton 神经流的图神经网络大大提高了对抗扰动的鲁棒性。