How Robust Are Graph Neural Networks to Structural Noise?

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.

[1]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[2]  Le Song,et al.  Adversarial Attack on Graph Structured Data , 2018, ICML.

[3]  Albert-László Barabási,et al.  Error and attack tolerance of complex networks , 2000, Nature.

[4]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[5]  Jure Leskovec,et al.  Learning Structural Node Embeddings via Diffusion Wavelets , 2017, KDD.

[6]  Kurt Mehlhorn,et al.  Weisfeiler-Lehman Graph Kernels , 2011, J. Mach. Learn. Res..

[7]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[8]  Réka Albert,et al.  correction: Error and attack tolerance of complex networks , 2001, Nature.

[9]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[10]  Danai Koutra,et al.  RolX: structural role extraction & mining in large graphs , 2012, KDD.

[11]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[12]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[13]  Jure Leskovec,et al.  Position-aware Graph Neural Networks , 2019, ICML.

[14]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[15]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[16]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[17]  Mathieu Bastian,et al.  Gephi: An Open Source Software for Exploring and Manipulating Networks , 2009, ICWSM.

[18]  F. Radicchi,et al.  Benchmark graphs for testing community detection algorithms. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.