Graph neural networks (GNNs) are an emerging model for learning graph embeddings and making predictions on graph structured data. However, robustness of graph neural networks is not yet well-understood. In this work, we focus on node structural identity predictions, where a representative GNN model is able to achieve near-perfect accuracy. We also show that the same GNN model is not robust to addition of structural noise, through a controlled dataset and set of experiments. Finally, we show that under the right conditions, graph-augmented training is capable of significantly improving robustness to structural noise.
@article{arxiv.1912.10206,
title = {How Robust Are Graph Neural Networks to Structural Noise?},
author = {James Fox and Sivasankaran Rajamanickam},
journal= {arXiv preprint arXiv:1912.10206},
year = {2019}
}
Comments
Accepted workshop paper at Deep Learning on Graphs: Methodologies and Applications (DLGMA'20)