Learning graph structure via graph convolutional networks
文献类型：期刊论文
| 作者 | Zhang, Qi1,2 ; Chang, Jianlong1,2; Meng, Gaofeng1; Xu, Shibiao1; Xiang, Shiming1,2; Pan, Chunhong1
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2019-11-01 |
| 卷号 | 95页码:308-318 |
| ISSN号 | 0031-3203 |
| 关键词 | Deep learning Graph convolutional neural networks Graph structure learning Changeable kernel sizes |
| DOI | 10.1016/j.patcog.2019.06.012 |
| 通讯作者 | Meng, Gaofeng(gfmeng@nlpr.ia.ac.cn) |
| 英文摘要 | Graph convolutional neural networks have aroused more and more attentions on account of the ability to handle the graph-structured data defined on irregular or non-Euclidean domains. Different from the data defined on regular grids, each node in the graph-structured data has different number of neighbors, and the interactions and correlations between nodes vary at different locations, resulting in complex graph structure. However, the existing graph convolutional neural networks generally pay little attention to exploiting the graph structure information. Moreover, most existing graph convolutional neural networks employ the weight sharing strategy which lies on the statistical assumption of stationarity. This assumption is not always verified on the graph-structured data. To address these issues, we propose a method that learns Graph Structure via graph Convolutional Networks (GSCN), which introduces the graph structure parameters measuring the correlation degrees of adjacent nodes. The graph structure parameters are constantly modified the graph structure during the training phase and will help the filters of the proposed method to focus on the relevant nodes in each neighborhood. Meanwhile by combining the graph structure parameters and kernel weights, our method, which relaxes the restriction of weight sharing, is better to handle the graph-structured data of non-stationarity. In addition, the non-linear activation function ReLU and the sparse constraint are employed on the graph structure parameters to promote GSCN to focus on the important links and filter out the insignificant links in each neighborhood. Experiments on various tasks, including text categorization, molecular activity detection, traffic forecasting and skeleton-based action recognition, illustrate the validity of our method. (C) 2019 Elsevier Ltd. All rights reserved. |
| WOS关键词 | NEURAL-NETWORK |
| 资助项目 | National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61620106003] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | ELSEVIER SCI LTD |
| WOS记录号 | WOS:000478710600026 |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27750]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Meng, Gaofeng |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Qi,Chang, Jianlong,Meng, Gaofeng,et al. Learning graph structure via graph convolutional networks[J]. PATTERN RECOGNITION,2019,95:308-318. |
| APA | Zhang, Qi,Chang, Jianlong,Meng, Gaofeng,Xu, Shibiao,Xiang, Shiming,&Pan, Chunhong.(2019).Learning graph structure via graph convolutional networks.PATTERN RECOGNITION,95,308-318. |
| MLA | Zhang, Qi,et al."Learning graph structure via graph convolutional networks".PATTERN RECOGNITION 95(2019):308-318. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。