On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
This work addresses the stability of graph neural networks for researchers and practitioners, but it is incremental as it builds on existing bounds by making them more interpretable.
The paper tackles the problem of understanding the stability of graph neural networks to small perturbations in graph topology, specifically edge rewiring, and develops an interpretable upper bound showing that these networks are stable to rewiring between high-degree nodes.
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.