Unsupervised/self-supervised graph neural networks (GNN) are vulnerable to inherent randomness in the input graph data which greatly affects the performance of the model in downstream tasks. In this paper, we alleviate the interference of graph randomness and learn appropriate representations of nodes without label information. To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy. We analyze the property of intrinsic connectivity and define intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. We then introduce structural entropy in the objective function to capture such a graph. Extensive experiments conducted on clustering and link prediction tasks under random-noises and meta-attack over three datasets show USER outperforms benchmarks and is robust to heavier randomness.

翻译：无监督/自监督图神经网络（GNN）易受输入图数据中固有随机性的干扰，这极大影响了模型在下游任务中的性能。本文旨在缓解图随机性的干扰，并在无标签信息的情况下学习节点的合适表示。为此，我们提出USER，一种基于结构熵的无监督鲁棒图神经网络。我们分析了内在连通性的性质并定义了内在连通性图。同时，我们识别出邻接矩阵的秩作为揭示提供与内在连通性图相同嵌入的图的关键因素。随后，我们在目标函数中引入结构熵以捕获此类图。在三个数据集上进行的聚类和链接预测任务实验（包括随机噪声和元攻击场景）表明，USER优于基准方法，且对更强的随机性具有鲁棒性。