论文标题
关于图神经扩散到拓扑扰动的鲁棒性
On the Robustness of Graph Neural Diffusion to Topology Perturbations
论文作者
论文摘要
图形上的神经扩散是一类新型的图形神经网络，最近引起了越来越多的关注。图形神经部分微分方程（PDE）的能力在解决图形神经网络（GNN）的常见障碍方面的能力，例如过度光滑和瓶颈的问题，但尚未对其对逆性攻击的稳健性。在这项工作中，我们探讨了图神经PDE的稳健性。我们从经验上证明，与其他GNN相比，图形神经PDE在拓扑扰动上本质上更强。我们通过在图形拓扑扰动下利用热半群的稳定性来提供对这一现象的见解。我们讨论各种图扩散操作员，并将它们与现有的图神经PDE相关联。此外，我们提出了一个一般图形神经PDE框架，基于该框架，可以定义一类新的强大GNN。我们验证了新模型在多个基准数据集上实现了可比的最新性能。
Neural diffusion on graphs is a novel class of graph neural networks that has attracted increasing attention recently. The capability of graph neural partial differential equations (PDEs) in addressing common hurdles of graph neural networks (GNNs), such as the problems of over-smoothing and bottlenecks, has been investigated but not their robustness to adversarial attacks. In this work, we explore the robustness properties of graph neural PDEs. We empirically demonstrate that graph neural PDEs are intrinsically more robust against topology perturbation as compared to other GNNs. We provide insights into this phenomenon by exploiting the stability of the heat semigroup under graph topology perturbations. We discuss various graph diffusion operators and relate them to existing graph neural PDEs. Furthermore, we propose a general graph neural PDE framework based on which a new class of robust GNNs can be defined. We verify that the new model achieves comparable state-of-the-art performance on several benchmark datasets.
