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. 数学与系统科学研究院
  3. 中国科学院数学与系统科学研究院
  4. 应用数学研究所
API-GNN: attribute preserving oriented interactive graph neural network

文献类型：期刊论文

作者Zhou, Yuchen1,2; Shang, Yanmin1,2; Cao, Yanan1,2; Li, Qian3; Zhou, Chuan1,4; Xu, Guandong3
刊名WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
出版日期2022-01-23
页码20
关键词Data mining Graph neural networks Social analysis Representation learning
ISSN号1386-145X
DOI10.1007/s11280-021-00987-z
英文摘要Attributed graph embedding aims to learn node representation based on the graph topology and node attributes. The current mainstream GNN-based methods learn the representation of the target node by aggregating the attributes of its neighbor nodes. These methods still face two challenges: (1) In the neighborhood aggregation procedure, the attributes of each node would be propagated to its neighborhoods which may cause disturbance to the original attributes of the target node and cause over-smoothing in GNN iteration. (2) Because the representation of the target node is derived from the attributes and topology of its neighbors, the attributes and topological information of each neighbor have different effects on the representation of the target node. However, this different contribution has not been considered by the existing GNN-based methods. In this paper, we propose a novel GNN model named API-GNN (Attribute Preserving Oriented Interactive Graph Neural Network). API-GNN can not only reduce the disturbance of neighborhood aggregation to the original attribute of target node, but also explicitly model the different impacts of attribute and topology on node representation. We conduct experiments on six public real-world datasets to validate API-GNN on node classification and link prediction. Experimental results show that our model outperforms several strong baselines over various graph datasets on multiple graph analysis tasks.
资助项目Youth Innovation Promotion Association CAS[2018192] ; National Natural Science Foundation of China[61902394]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000745550000001
出版者SPRINGER
源URL[http://ir.amss.ac.cn/handle/2S8OKBNM/59899]  
专题应用数学研究所
通讯作者Shang, Yanmin
作者单位1.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China
3.Univ Technol Sydney, Sydney, NSW, Australia
4.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhou, Yuchen,Shang, Yanmin,Cao, Yanan,et al. API-GNN: attribute preserving oriented interactive graph neural network[J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,2022:20.
APA Zhou, Yuchen,Shang, Yanmin,Cao, Yanan,Li, Qian,Zhou, Chuan,&Xu, Guandong.(2022).API-GNN: attribute preserving oriented interactive graph neural network.WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,20.
MLA Zhou, Yuchen,et al."API-GNN: attribute preserving oriented interactive graph neural network".WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS (2022):20.

入库方式： OAI收割

来源：数学与系统科学研究院

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。