Corpus ID: 220363476

Simple and Deep Graph Convolutional Networks

  title={Simple and Deep Graph Convolutional Networks},
  author={M. Chen and Zhewei Wei and Zengfeng Huang and B. Ding and Y. Li},
  • M. Chen, Zhewei Wei, +2 authors Y. Li
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the over-smoothing problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Implicit Graph Neural Networks
    • 1
    • Highly Influenced
    • PDF
    Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
    Understanding and Visualizing Graph Neural Networks
    Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
    Learning to Infer Unseen Attribute-Object Compositions
    On Graph Neural Networks versus Graph-Augmented MLPs


    Publications referenced by this paper.
    Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
    • 383
    • PDF
    Simplifying Graph Convolutional Networks
    • 270
    • Highly Influential
    • PDF
    FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
    • 318
    • PDF
    Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
    • 2,230
    • PDF
    DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
    • 59
    • Highly Influential
    Self-Attention Graph Pooling
    • 110
    • PDF
    Stochastic Training of Graph Convolutional Networks with Variance Reduction
    • 123
    • PDF
    Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
    • 87
    • PDF
    Graph U-Nets
    • 108
    • PDF
    Semi-Supervised Classification with Graph Convolutional Networks
    • 4,791
    • Highly Influential
    • PDF