On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

Illustration of Position vs. Structure: A and B are “positionally close”– having relatively close positions in the global network, whereas A and C are “structurally close”– having relatively similar local neighborhood structures.
Proceedings of the International Conference on Information and Knowledge Management

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.