论文标题
学习节点表示反对扰动
Learning Node Representations against Perturbations
论文作者
论文摘要
最近的图神经网络（GNN）在节点表示学习中取得了显着的性能。 GNN成功的关键因素之一是节点表示上的\ emph {平滑度}属性。尽管如此，大多数GNN模型都易受图形输入的扰动，并且可以学习不可靠的节点表示。在本文中，我们研究了如何学习针对GNN中扰动的节点表示。具体而言，我们认为在输入的轻微扰动下应保持节点表示形式，并且应识别来自不同结构的节点表示，分别将两个称为\ emph {styability}和\ emph {sidentifiability}在节点表示上。为此，我们提出了一个新型模型，称为稳定性可识别性GNN针对扰动（SignNap），该模型以无监督的方式学习可靠的节点表示形式。 SignNap通过对比度目标正式化\ emph {稳定性}和\ emph {dissinifiability}，并用现有的GNN骨架保留\ emph {平滑度}。提出的方法是一个通用框架，可以配备许多其他主链模型（例如GCN，GraphSage和GAT）。在节点分类的转导和电感学习设置下，对六个基准测试的广泛实验证明了我们方法的有效性。代码和数据可在线获得：〜\ url {https://github.com/xuchensjtu/signnap-master-online}
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}
