基于多通道的边学习图卷积网络

杨帅; 王瑞琴; 马辉

doi:10.11959/j.issn.1000-0801.2022250

您当前的位置：

首页 >

文章列表页 >

基于多通道的边学习图卷积网络

研究与开发 | 更新时间：2024-06-05

- 基于多通道的边学习图卷积网络
- Multi-channel based edge-learning graph convolutional network
- 电信科学 2022年38卷第9期页码：95-104
- 作者机构：
- 作者简介：
  
  [ "杨帅（1996- ），男，湖州师范学院信息工程学院硕士生，主要研究方向为机器学习、个性化推荐等" ]
  [ "王瑞琴（1979- ），女，博士，湖州师范学院信息工程学院教授，主要研究方向为机器学习、数据挖掘、社交网络分析以及个性化推荐等" ]
  [ "马辉（1997- ），男，湖州师范学院信息工程学院硕士生，主要研究方向为聚类、神经网络等" ]
- 基金信息：
  
  国家社会科学基金资助项目;The National Social Science Foundation of China(20BTQ093);浙江省自然科学基金资助项目;The Natural Science Foundation of Zhejiang Province(LY20F020006)
- DOI：10.11959/j.issn.1000-0801.2022250
  中图分类号： TP391
- 网络出版日期：2022-09，
  
  纸质出版日期：2022-09-20
- 稿件说明：
移动端阅览
杨帅, 王瑞琴, 马辉. 基于多通道的边学习图卷积网络[J]. 电信科学, 2022,38(9):95-104.

Shuai YANG, Ruiqin WANG, Hui MA. Multi-channel based edge-learning graph convolutional network[J]. Telecommunications science, 2022, 38(9): 95-104.
杨帅, 王瑞琴, 马辉. 基于多通道的边学习图卷积网络[J]. 电信科学, 2022,38(9):95-104. DOI： 10.11959/j.issn.1000-0801.2022250.

Shuai YANG, Ruiqin WANG, Hui MA. Multi-channel based edge-learning graph convolutional network[J]. Telecommunications science, 2022, 38(9): 95-104. DOI： 10.11959/j.issn.1000-0801.2022250.

摘要

通常图的边包含了图的重要信息，然而目前大多数用于图学习的深度学习模型（如图卷积网络（graph convolutional network，GCN）和图注意力网络（graph attention network，GAT））没有充分利用多维边特征的特性；另一个问题是图中可能存在噪声，影响图学习的性能。使用多层感知机对图数据进行去噪优化处理，在GCN的基础上引入了多通道学习边特征的方法，对图的多维边属性进行编码，按原始图所包含的属性分别建模为多通道，每个通道对应一种边特征属性对图节点进行约束训练，可以让算法更合理地学习图中多维边特征，在Cora、Tox21、Freesolv等数据集上的实验证明了去噪方法与多通道方法的有效性。

Abstract

Usually the edges of the graph contain important information of the graph.However

most of deep learning models for graph learning

such as graph convolutional network (GCN) and graph attention network (GAT)

do not fully utilize the characteristics of multi-dimensional edge features.Another problem is that there may be noise in the graph that affects the performance of graph learning.Multilayer perceptron (MLP) was used to denoise and optimize the graph data

and a multi-channel learning edge feature method was introduced on the basis of GCN.The multi-dimensional edge attributes of the graph were encoded

and the attributes contained in the original graph were modeled as multi-channel.Each channel corresponds to an edge feature attribute to constrain the training of graph nodes

which allows the algorithm to learn multi-dimensional edge features in the graph more reasonably.Experiments based on Cora

Tox21

Freesolv and other datasets had proved the effectiveness of denoising methods and multi-channel methods.

关键词

Keywords

references

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

DEFFERRARD M , BRESSON X , VANDERGHEYNST P . Convolutional neural networks on graphs with fast localized spectral filtering [C ] // Proceedings of 30th Conference on Neural Information Processing Systems . New York:ACM Press , 2016 .

KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks [C ] // Proceedings of 5th International Conference on Learning Representations(ICLR 2017) .[S.l.:s.n. ] , 2017 .

VELIČKOVIĆ P , CUCURULL G , CASANOVA A , et al . Graph attention networks [C ] // Proceedings of 6th International Conference on Learning Representations(ICLR 2018) .[S.l.:s.n. ] , 2018 .

BRUNA J , ZAREMBA W , SZLAM A , et al . Spectral networks and deep locally connected networks on graphs [C ] // Proceedings of 2nd International Conference on Learning Representations . Netherlands:Elsevier Press , 2014 .

GONG L , CHENG Q . Exploiting edge features for graph neural networks [C ] // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2019 .

CHEN P , LIU W , HSIEH C Y , et al . Utilizing edge features in graph neural networks via variational information maximization [J ] . arXiv preprint arXiv:1906.05488 , 2019 .

GILMER J , SCHOENHOLZ S S , RILEY P F , et al . Neural message passing for quantum chemistry [C ] // Proceedings of the 34th International Conference on Machine Learning . New York:ACM Press , 2017 .

HAMILTON W , YING Z , LESKOVEC J . Inductive representation learning on large graphs [C ] // Proceedings of 31st Conference on Neural Information Processing Systems . New York:ACM Press , 2017 .

LI Q , HAN Z , WU X M . Deeper insights into graph convolutional networks for semi-supervised learning [C ] // Proceedings of 32nd AAAI Onference on Artificial Intelligence . New York:ACM Press , 2018 .

SUN K , LIN Z , ZHU Z . Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes [C ] // Proceedings of the 34th AAAI Conference on Artificial Intelligence . Palo Alto:AAAI Press , 2020 : 5892 - 5899 .

CARON M , BOJANOWSKI P , JOULIN A , et al . Deep clustering for unsupervised learning of visual features [C ] // Proceedings of the European Conference on Computer Vision . New York:Springer Press , 2018 : 132 - 149 .

YANG H , MA K , CHENG J . Rethinking graph regularization for graph neural networks [C ] // Proceedings of the 35th AAAI Conference on Artificial Intelligence . Palo Alto:AAAI Press , 2021 : 4573 - 4581 .

YING Z , YOU J , MORRIS C , et al . Hierarchical graph representation learning with differentiable pooling [C ] // Proceedings of 32nd Conference on Neural Information Processing Systems . New York:ACM Press , 2018 .

WU Z , RAMSUNDAR B , FEINBERG E N , et al . MoleculeNet:a benchmark for molecular machine learning [J ] . Chemical science , 2018 , 9 ( 2 ): 513 - 530 .

浏览量

386

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据