Recent graph neural networks (GNN) has achieved remarkable performance in node representation learning. One key factor of GNN's success is the \emph{smoothness} property on node representations. Despite this, most GNN models are fragile to the perturbations on graph inputs and could learn unreliable node representations. In this paper, we study how to learn node representations against perturbations in GNN. Specifically, we consider that a node representation should remain stable under slight perturbations on the input, and node representations from different structures should be identifiable, which two are termed as the \emph{stability} and \emph{identifiability} on node representations, respectively. To this end, we propose a novel model called Stability-Identifiability GNN Against Perturbations (SIGNNAP) that learns reliable node representations in an unsupervised manner. SIGNNAP formalizes the \emph{stability} and \emph{identifiability} by a contrastive objective and preserves the \emph{smoothness} with existing GNN backbones. The proposed method is a generic framework that can be equipped with many other backbone models (e.g. GCN, GraphSage and GAT). Extensive experiments on six benchmarks under both transductive and inductive learning setups of node classification demonstrate the effectiveness of our method. Codes and data are available online:~\url{https://github.com/xuChenSJTU/SIGNNAP-master-online}

翻译：近期，图神经网络（GNN）在节点表示学习方面取得了显著成效。GNN成功的关键因素之一在于节点表示的平滑性。尽管如此，大多数GNN模型对图输入的扰动较为脆弱，可能学习到不可靠的节点表示。本文研究如何在GNN中学习抗扰动的节点表示。具体而言，我们认为节点表示应在输入发生轻微扰动时保持稳定，且来自不同结构的节点表示应具有可辨识性，这两者分别称为节点表示的稳定性与可辨识性。为此，我们提出一种名为SIGNNAP（Stability-Identifiability GNN Against Perturbations）的新型模型，该模型以无监督方式学习可靠的节点表示。SIGNNAP通过对比目标形式化定义了稳定性与可辨识性，并借助现有GNN主干网络保留平滑性。所提方法是一个通用框架，可适配多种主干模型（如GCN、GraphSage和GAT）。在节点分类的直推式与归纳式学习设置下，基于六个基准数据集的大量实验验证了本方法的有效性。代码与数据在线提供：~\url{https://github.com/xuChenSJTU/SIGNNAP-master-online}