Simplified multilayer graph convolutional networks with dropout
Simplified multilayer graph convolutional networks with dropout
复制标题
带 dropout 的简化多层图卷积网络
DOI:
10.1007/s10489-021-02617-7
复制
发表时间:
2021-07
影响因子:
5.3
通讯作者:
Shiming Tao
中科院分区:
文献类型:
--
作者:
Fei Yang;Huyin Zhang;Shiming Tao
Graph convolutional networks (GCNs) and their variants are excellent deep learning methods for graph-structured data. Moreover, multilayer GCNs can perform feature smoothing repeatedly, which creates considerable performance improvements. However, they may inherit unnecessary complexity and redundant computation; to make matters worse, they introduce overfitting as the number of layers increases. In this paper, we present simplified multilayer graph convolutional networks with dropout (DGCs), novel neural network architectures that successively perform nonlinearity removal and weight matrix merging between graph conventional layers, leveraging a dropout layer to achieve feature augmentation and effectively reduce overfitting. Under such circumstances, first, we extend a shallow GCN to a multilayer GCN. Then, we reduce the complexity and redundant calculations of the multilayer GCN, while improving its classification performance. Finally, we make DGCs readily applicable to inductive and transductive tasks. Extensive experiments on citation networks and social networks offer evidence that the proposed model matches or outperforms state-of-the-art methods.
登录
查看更多内容
DOI:
10.1109/tpami.2017.2784440
发表时间:
2018-12-01
影响因子:
23.6
作者:
Achille, Alessandro;Soatto, Stefano
通讯作者:
Soatto, Stefano
DOI:
10.1201/b17320-16
发表时间:
2008-09
期刊:
--
影响因子:
--
作者:
Prithviraj Sen;Galileo Namata;M. Bilgic;L. Getoor;Brian Gallagher;Tina Eliassi-Rad
通讯作者:
Prithviraj Sen;Galileo Namata;M. Bilgic;L. Getoor;Brian Gallagher;Tina Eliassi-Rad
DOI:
--
发表时间:
2019-05
期刊:
--
影响因子:
--
作者:
Shengjie Wang;Tianyi Zhou;J. Bilmes
通讯作者:
Shengjie Wang;Tianyi Zhou;J. Bilmes
DOI:
--
发表时间:
2018-03
期刊:
--
影响因子:
--
作者:
Jiani Zhang;Xingjian Shi;Junyuan Xie;Hao Ma;Irwin King;D. Yeung
通讯作者:
Jiani Zhang;Xingjian Shi;Junyuan Xie;Hao Ma;Irwin King;D. Yeung
DOI:
10.1016/j.neunet.2019.03.013
发表时间:
2019-07
期刊:
Neural networks : the official journal of the International Neural Network Society
影响因子:
--
作者:
Dazhi Zhao;Guozhu Yu;Peng Xu;M. Luo
通讯作者:
Dazhi Zhao;Guozhu Yu;Peng Xu;M. Luo