Corpus ID: 211532552

Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks

@article{Chen2020BridgingTG,
  title={Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks},
  author={Zhiqian Chen and Fanglan Chen and Lei Zhang and Taoran Ji and Kaiqun Fu and Liang Zhao and Feng Chen and Chang-Tien Lu},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.11867}
}
  • Zhiqian Chen, Fanglan Chen, +5 authors Chang-Tien Lu
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • The success of deep learning has been widely recognized in many machine learning tasks during the last decades, ranging from image classification and speech recognition to natural language understanding. As an extension of deep learning, Graph neural networks (GNNs) are designed to solve the non-Euclidean problems on graph-structured data which can hardly be handled by general deep learning techniques. Existing GNNs under various mechanisms, such as random walk, PageRank, graph convolution, and… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 68 REFERENCES

    A Comprehensive Survey on Graph Neural Networks

    VIEW 2 EXCERPTS

    Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs

    VIEW 2 EXCERPTS

    Deep Learning on Graphs: A Survey

    VIEW 2 EXCERPTS

    Graph Neural Networks: A Review of Methods and Applications

    VIEW 2 EXCERPTS