Corpus ID: 222209152

Simplicial Neural Networks

@article{Ebli2020SimplicialNN,
  title={Simplicial Neural Networks},
  author={Stefania Ebli and Michael Defferrard and Gard Spreemann},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.03633}
}
  • Stefania Ebli, Michael Defferrard, Gard Spreemann
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural multi-dimensional extensions of graphs that encode not only pairwise relationships but also higher-order interactions between vertices - allowing us to consider richer data, including vector fields and $n$-fold collaboration networks. We define an appropriate notion of convolution that we leverage to construct… CONTINUE READING

    Figures and Tables from this paper.

    References

    SHOWING 1-10 OF 31 REFERENCES
    LEARNING FROM SIGNALS DEFINED OVER SIMPLICIAL COMPLEXES
    • 11
    • PDF
    MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK FOR DIRECTED GRAPHS
    • 33
    • Highly Influential
    • PDF
    Spectral Networks and Locally Connected Networks on Graphs
    • 1,677
    • PDF
    Group Equivariant Convolutional Networks
    • 534
    • PDF
    Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
    • 2,327
    • PDF
    Geometric Deep Learning: Going beyond Euclidean data
    • 1,145
    • PDF
    Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
    • 25
    • PDF
    Analyzing collaboration networks using simplicial complexes: A case study
    • 20
    • PDF
    DeepSphere: a graph-based spherical CNN
    • 4
    On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
    • 151
    • PDF