Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where the superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones. In this paper, we point out the two types of artificial node features,i.e., positional and structural node features, and provide insights on why each of them is more appropriate for certain tasks,i.e., positional node classification, structural node classification, and graph classification. Extensive experimental results on 10 benchmark datasets validate our insights, thus leading to a practical guideline on the choices between different artificial node features for GNNs on non-attributed graphs. The code is available at https://github.com/zjzijielu/gnn-exp/.

本文介绍了两种构建人工节点特征的类型，包括位置和结构节点特征，并提供了对于每一种任务，即位置节点分类、结构节点分类和图分类，为什么每种节点特征更加适合的见解。此外，通过在10个基准数据集上进行广泛实验，验证了我们的洞察力，从而为非属性图上的GNN不同人工节点特征之间的选择提供了实用指南。

关于非属性图上基于位置和结构节点的图神经网络特征