On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
arXiv:2010.13747
Abstract
Graph neural networks are experiencing a surge of popularity within the machine learning community due to their ability to adapt to non-Euclidean domains and instil inductive biases. Despite this, their stability, i.e., their robustness to small perturbations in the input, is not yet well understood. Although there exists some results showing the stability of graph neural networks, most take the form of an upper bound on the magnitude of change due to a perturbation in the graph topology. However, the change in the graph topology captured in existing bounds tend not to be expressed in terms of structural properties, limiting our understanding of the model robustness properties. In this work, we develop an interpretable upper bound elucidating that graph neural networks are stable to rewiring between high degree nodes. This bound and further research in bounds of similar type provide further understanding of the stability properties of graph neural networks.
arXiv commentTo appear at the 46th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
References in corpus (13)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Geometric deep learning: going beyond Euclidean data
- Simplifying Graph Convolutional Networks
- Adversarial Attacks on Neural Networks for Graph Data
- Graph Neural Networks with convolutional ARMA filters
- Graph signal processing for machine learning: A review and new perspectives
- Stability Properties of Graph Neural Networks
- On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning
- Filtering Random Graph Processes Over Random Time-Varying Graphs
- Attacking Graph Convolutional Networks via Rewiring
- Certifiable Robustness to Graph Perturbations
- Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
- Stability and Generalization of Graph Convolutional Neural Networks