A Deep Graph Structured Clustering Network
Graph clustering is a fundamental task in data analysis and has attracted considerable attention in recommendation systems, mapping knowledge domain, and biological science. Because graph convolution is very effective in combining the feature information and topology information of graph data, some...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9181620/ |
| _version_ | 1818379518006525952 |
|---|---|
| author | Xunkai Li Youpeng Hu Yaoqi Sun Ji Hu Jiyong Zhang Meixia Qu |
| author_facet | Xunkai Li Youpeng Hu Yaoqi Sun Ji Hu Jiyong Zhang Meixia Qu |
| author_sort | Xunkai Li |
| collection | DOAJ |
| description | Graph clustering is a fundamental task in data analysis and has attracted considerable attention in recommendation systems, mapping knowledge domain, and biological science. Because graph convolution is very effective in combining the feature information and topology information of graph data, some graph clustering methods based on graph convolution have achieved superior performance. However, current methods lack the consideration of structured information and the process of graph convolution. Specifically, most of existing methods ignore the implicit interaction between topology information and feature information, and the stacking of a small number of graph convolutional layers leads to insufficient learning of complex information. Inspired by graph convolutional network and auto-encoder, we propose a deep graph structured clustering network that applies a deep clustering method to graph structured data processing. Deep graph convolution is employed in the backbone network, and evaluates the result of each iteration with node feature and topology information. In order to optimize the network without supervision, a triple self-supervised module is designed to help update parameters for overall network. In our model, we exploit all information of the graph structured data and perform self-supervised learning. Furthermore, improved graph convolution layers significantly alleviate the problem of clustering performance degradation caused by over-smoothing. Our model is designed to perform on representative and indirect graph datasets, and experimental results demonstrate that our model achieves superior performance over state-of-the-art models. |
| first_indexed | 2024-12-14T02:04:03Z |
| format | Article |
| id | doaj.art-80709615459f42f7b98c8760cdd85f31 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T02:04:03Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-80709615459f42f7b98c8760cdd85f312022-12-21T23:20:56ZengIEEEIEEE Access2169-35362020-01-01816172716173810.1109/ACCESS.2020.30201929181620A Deep Graph Structured Clustering NetworkXunkai Li0https://orcid.org/0000-0002-1230-7603Youpeng Hu1https://orcid.org/0000-0003-2097-5879Yaoqi Sun2https://orcid.org/0000-0001-8874-241XJi Hu3https://orcid.org/0000-0002-1806-6070Jiyong Zhang4https://orcid.org/0000-0001-9600-8477Meixia Qu5https://orcid.org/0000-0001-7607-8195School of Mechanical and Information Engineering, Shandong University, Weihai, ChinaSchool of Mechanical and Information Engineering, Shandong University, Weihai, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Electronic Information, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Mechanical and Information Engineering, Shandong University, Weihai, ChinaGraph clustering is a fundamental task in data analysis and has attracted considerable attention in recommendation systems, mapping knowledge domain, and biological science. Because graph convolution is very effective in combining the feature information and topology information of graph data, some graph clustering methods based on graph convolution have achieved superior performance. However, current methods lack the consideration of structured information and the process of graph convolution. Specifically, most of existing methods ignore the implicit interaction between topology information and feature information, and the stacking of a small number of graph convolutional layers leads to insufficient learning of complex information. Inspired by graph convolutional network and auto-encoder, we propose a deep graph structured clustering network that applies a deep clustering method to graph structured data processing. Deep graph convolution is employed in the backbone network, and evaluates the result of each iteration with node feature and topology information. In order to optimize the network without supervision, a triple self-supervised module is designed to help update parameters for overall network. In our model, we exploit all information of the graph structured data and perform self-supervised learning. Furthermore, improved graph convolution layers significantly alleviate the problem of clustering performance degradation caused by over-smoothing. Our model is designed to perform on representative and indirect graph datasets, and experimental results demonstrate that our model achieves superior performance over state-of-the-art models.https://ieeexplore.ieee.org/document/9181620/Autoencoderdeep graph convolutional networkdeep graph clusteringunsupervised learning |
| spellingShingle | Xunkai Li Youpeng Hu Yaoqi Sun Ji Hu Jiyong Zhang Meixia Qu A Deep Graph Structured Clustering Network IEEE Access Autoencoder deep graph convolutional network deep graph clustering unsupervised learning |
| title | A Deep Graph Structured Clustering Network |
| title_full | A Deep Graph Structured Clustering Network |
| title_fullStr | A Deep Graph Structured Clustering Network |
| title_full_unstemmed | A Deep Graph Structured Clustering Network |
| title_short | A Deep Graph Structured Clustering Network |
| title_sort | deep graph structured clustering network |
| topic | Autoencoder deep graph convolutional network deep graph clustering unsupervised learning |
| url | https://ieeexplore.ieee.org/document/9181620/ |
| work_keys_str_mv | AT xunkaili adeepgraphstructuredclusteringnetwork AT youpenghu adeepgraphstructuredclusteringnetwork AT yaoqisun adeepgraphstructuredclusteringnetwork AT jihu adeepgraphstructuredclusteringnetwork AT jiyongzhang adeepgraphstructuredclusteringnetwork AT meixiaqu adeepgraphstructuredclusteringnetwork AT xunkaili deepgraphstructuredclusteringnetwork AT youpenghu deepgraphstructuredclusteringnetwork AT yaoqisun deepgraphstructuredclusteringnetwork AT jihu deepgraphstructuredclusteringnetwork AT jiyongzhang deepgraphstructuredclusteringnetwork AT meixiaqu deepgraphstructuredclusteringnetwork |