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

Abstract

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where 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-positional-structural-node-features.

arXiv commentAccepted to CIKM 2022. The previous version is accepted for KDD-DLG Workshop 2021 (spotlight, no proceedings)

References in corpus (19)

• Inductive Representation Learning on Large Graphs
• struc2vec: Learning Node Representations from Structural Identity
• Variational Graph Auto-Encoders
• Link Prediction Based on Graph Neural Networks
• Design Space for Graph Neural Networks
• Graph Convolutional Networks for Graphs Containing Missing Features
• Supervised Community Detection with Line Graph Neural Networks
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
• Position-aware Graph Neural Networks
• Implicit Graph Neural Networks
• Rethinking pooling in graph neural networks
• Understanding Regularized Spectral Clustering via Graph Conductance
• A simple yet effective baseline for non-attributed graph classification
• Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• On the Equivalence between Positional Node Embeddings and Structural Graph Representations
• Random Features Strengthen Graph Neural Networks
• Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks

Cited by in corpus (5)

• Graph Neural Networks for Graph Drawing
• Graph Neural Networks with Learnable Structural and Positional Representations
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Deep Fraud Detection on Non-attributed Graph