中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
CNIM-GCN: Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks

文献类型：期刊论文

作者Zhu, Xiaofei2; Li, Chenghong2; Guo, Jiafeng3; Dietze, Stefan1,4
刊名EXPERT SYSTEMS WITH APPLICATIONS
出版日期2023-09-15
卷号226页码:11
关键词Network representation learning Deep learning Graph convolutional networks Node classification
ISSN号0957-4174
DOI10.1016/j.eswa.2023.120178
英文摘要Node classification plays a critical role in numerous network applications, and has attracted increasing attention in recent years. Existing state-of-the-art studies aim at maintaining common information between the topology graph and the feature graph in an implicit way, i.e., adopting a common convolution with parameter sharing strategy to preserve common information between the two graphs. Despite their effectiveness, these studies are still far from satisfactory due to the complex correlation information between the two spaces. To address this issue, we present a novel method named Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks (CNIM-GCN). CNIM-GCN preserves the common information between the feature space and topology space in an explicit way by introducing a consensus graph for information propagation. A multi-channel graph convolutional networks is developed for effectively fusing information from different graphs. In addition, we further incorporate two types of consistency constraints, i.e., structural consistency constraint and reconstruction consistency constraint, to maintain the consistency between different channels. The former is leveraged to keep the consistency between different spaces at the structural relationship level, while the latter is used to preserve a consistency between the final node representation and the original node feature representation. We carry out extensive experiments on five real-world datasets, including ACM, BlogCatalog, CiteSeer, Flickr and UAI2010. Experimental results show that our proposed approach CNIM-GCN is superior to the state-of-the-art baselines.
资助项目National Natural Science Founda-tion of China[62141201] ; Major Project of Science and Technology Research Program of Chongqing Education Commis-sion of China[KJZD-M202201102] ; Natural Sci-ence Foundation of Chongqing, China[CSTB2022NSCQ-MSX1672] ; Federal Ministry of Education and Research, Germany[01IS21086]
WOS研究方向Computer Science ; Engineering ; Operations Research & Management Science
语种英语
WOS记录号WOS:000988858400001
出版者PERGAMON-ELSEVIER SCIENCE LTD
源URL[http://119.78.100.204/handle/2XEOYT63/21429]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhu, Xiaofei
作者单位1.Heinrich Heine Univ Dusseldorf, Inst Comp Sci, D-40225 Dusseldorf, Germany
2.Chongqing Univ Technol, Coll Comp Sci & Engn, Chongqing 400054, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Leibniz Inst Social Sci, Knowledge Technol Social Sci, D-50667 Cologne, Germany
推荐引用方式
GB/T 7714		 Zhu, Xiaofei,Li, Chenghong,Guo, Jiafeng,et al. CNIM-GCN: Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks[J]. EXPERT SYSTEMS WITH APPLICATIONS,2023,226:11.
APA Zhu, Xiaofei,Li, Chenghong,Guo, Jiafeng,&Dietze, Stefan.(2023).CNIM-GCN: Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks.EXPERT SYSTEMS WITH APPLICATIONS,226,11.
MLA Zhu, Xiaofei,et al."CNIM-GCN: Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks".EXPERT SYSTEMS WITH APPLICATIONS 226(2023):11.

入库方式： OAI收割

来源：计算技术研究所

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。