Corpus ID: 152282530

Stability Properties of Graph Neural Networks

@article{Gama2019StabilityPO,
  title={Stability Properties of Graph Neural Networks},
  author={F. Gama and Joan Bruna and A. Ribeiro},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.04497}
}
  • F. Gama, Joan Bruna, A. Ribeiro
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Data stemming from networks exhibit an irregular support, whereby each data element is related by arbitrary pairwise relationships determined by the network. Graph neural networks (GNNs) have emerged as information processing architectures that exploit the particularities of this underlying support. The use of nonlinearities in GNNs, coupled with the fact that filters are learned from data, raises mathematical challenges that have precluded the development of theoretical results that would give… CONTINUE READING

    Figures and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 24 CITATIONS

    Stability of Graph Neural Networks to Relative Perturbations

    • F. Gama, Joan Bruna, A. Ribeiro
    • Mathematics, Computer Science, Engineering
    • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2020
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Graphs, Convolutions, and Neural Networks

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    EdgeNets: Edge Varying Graph Neural Networks

    VIEW 7 EXCERPTS
    CITES BACKGROUND

    Transferability of Spectral Graph Convolutional Neural Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Stochastic Graph Neural Networks

    On The Stability of Polynomial Spectral Graph Filters

    Invariance-Preserving Localized Activation Functions for Graph Neural Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Spatial Gating Strategies for Graph Recurrent Neural Networks

    • Luana Ruiz, F. Gama, A. Ribeiro
    • Computer Science
    • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2020
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Graphon Signal Processing

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2019
    2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 59 REFERENCES

    Network Topology Inference from Spectral Templates

    VIEW 1 EXCERPT

    EdgeNets: Edge Varying Graph Neural Networks

    Convolutional Graph Neural Networks

    VIEW 1 EXCERPT

    Convolutional Neural Network Architectures for Signals Supported on Graphs

    VIEW 1 EXCERPT

    On the Transferability of Spectral Graph Filters