API-GNN: attribute preserving oriented interactive graph neural network

doi:10.1007/s11280-021-00987-z

CSpace > 应用数学研究所

	API-GNN: attribute preserving oriented interactive graph neural network
	Zhou, Yuchen 1,2; Shang, Yanmin 1,2; Cao, Yanan 1,2; Li, Qian 3; Zhou, Chuan1,4 ; Xu, Guandong 3
	2022-01-23
发表期刊	WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
ISSN	1386-145X
页码	20
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.
关键词	Data mining Graph neural networks Social analysis Representation learning
DOI	10.1007/s11280-021-00987-z
收录类别	SCI
语种	英语
资助项目	Youth Innovation Promotion Association CAS[2018192] ; National Natural Science Foundation of China[61902394]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000745550000001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/59900
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.