Multi-channel based edge-learning graph convolutional network
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...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2022-09-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022250/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530666325377024 |
|---|---|
| author | Shuai YANG Ruiqin WANG Hui MA |
| author_facet | Shuai YANG Ruiqin WANG Hui MA |
| author_sort | Shuai YANG |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-5913aa2e872d4764949b6e82f89467f6 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2022-09-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-5913aa2e872d4764949b6e82f89467f62025-01-15T03:00:09ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012022-09-01389510459577151Multi-channel based edge-learning graph convolutional networkShuai YANGRuiqin WANGHui MAUsually 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.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022250/graph convolutional networkedge featuregraph denoisingmulti-channeledge-learning |
| spellingShingle | Shuai YANG Ruiqin WANG Hui MA Multi-channel based edge-learning graph convolutional network Dianxin kexue graph convolutional network edge feature graph denoising multi-channel edge-learning |
| title | Multi-channel based edge-learning graph convolutional network |
| title_full | Multi-channel based edge-learning graph convolutional network |
| title_fullStr | Multi-channel based edge-learning graph convolutional network |
| title_full_unstemmed | Multi-channel based edge-learning graph convolutional network |
| title_short | Multi-channel based edge-learning graph convolutional network |
| title_sort | multi channel based edge learning graph convolutional network |
| topic | graph convolutional network edge feature graph denoising multi-channel edge-learning |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022250/ |
| work_keys_str_mv | AT shuaiyang multichannelbasededgelearninggraphconvolutionalnetwork AT ruiqinwang multichannelbasededgelearninggraphconvolutionalnetwork AT huima multichannelbasededgelearninggraphconvolutionalnetwork |