article · arXiv (Cornell University) · 2020

Simple and Deep Graph Convolutional Networks

Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li

Cited by 399Open access

Abstract

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 {\em 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 simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

Cite this paper

APA 7

Chen, M., Wei, Z., Huang, Z., Ding, B., & Li, Y. (2020). Simple and Deep Graph Convolutional Networks. arXiv (Cornell University), 1, 1725–1735. https://doi.org/10.48550/arxiv.2007.02133

MLA 9

Chen, Ming, et al. “Simple and Deep Graph Convolutional Networks.” arXiv (Cornell University), vol. 1, 2020, pp. 1725–35, https://doi.org/10.48550/arxiv.2007.02133.

Chicago

Chen, Ming, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. 2020. “Simple and Deep Graph Convolutional Networks.” arXiv (Cornell University) 1: 1725–35. https://doi.org/10.48550/arxiv.2007.02133.

Harvard

Chen, M. et al. (2020) ‘Simple and Deep Graph Convolutional Networks’, arXiv (Cornell University), 1, pp. 1725–1735. Available at: https://doi.org/10.48550/arxiv.2007.02133.

BibTeX

@article{chen2020simple,
  title = {{Simple and Deep Graph Convolutional Networks}},
  author = {Chen, Ming and Wei, Zhewei and Huang, Zengfeng and Ding, Bolin and Li, Yaliang},
  journal = {arXiv (Cornell University)},
  volume = {1},
  pages = {1725--1735},
  year = {2020},
  doi = {10.48550/arxiv.2007.02133}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.