Random Features Strengthen Graph Neural Networks

Understand

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks.

• Recently, the limitations of the expressive power of various GNN models have been revealed.
• For example, GNNs cannot distinguish some non-isomorphic graphs and they cannot learn efficient graph algorithms.
• In this paper, we demonstrate that GNNs become powerful just by adding a random feature to each node.