On Node Features for Graph Neural Networks
This addresses a limitation for researchers and practitioners using GNNs on non-attributed graphs, though it is incremental as it builds on existing GNN frameworks.
The paper tackles the problem of applying graph neural networks (GNNs) to featureless graphs by analyzing the impact of node features on performance and proposing new feature initialization methods. The result shows that artificial features are highly competitive with real features.
Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.