MEMN:Multiple Vectors Embedding for Multi-Label Networks

doi:10.1109/ACCESS.2018.2878870

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	MEMN:Multiple Vectors Embedding for Multi-Label Networks
	Liu, Zhuang 3,4; Pu, Juhua 3,4; Liu, Xingwu 1,2; Chen, Yujun 3,4
刊名	IEEE ACCESS
	2018
卷号	6 页码:66143-66152
关键词	Network embedding multiple vectors multi-label classification link prediction
ISSN号	2169-3536
DOI	10.1109/ACCESS.2018.2878870
英文摘要	Network embedding, which assigns vectors to network nodes in a manner that preserves the network features, is a hotspot of network research in recent years. A salient common feature of the existing approaches is that each node is mapped to exactly one vector. This one-vector mapping is insufficient to represent the nodes' attribution in those extensively existed networks whose nodes' have multiple labels. In this paper, we present MEMN, a novel approach of multiple vectors embedding for multi-labeled networks. For any node in the network, MEMN employs Node2vecWalk to generate its neighbor nodes. We maintain a neighbor cluster center for each label of the node and induce its label by clustering the embeddings of the neighbor nodes. Then, we assign vectors, one per label, to the node. This method can be non-parameterized, namely, NP-MEMN method. That is, if the number of label vectors for a node is not given, NP-MEMN can learn during embedding. Empirical studies on real datasets show that either MEMN or NP-MEMN outperforms many widely used methods in both multi-label classification and link prediction.
资助项目	National Key Research and Development Program of China[2017YFB1002000] ; National Natural Science Foundation of China[61502320] ; Science Foundation of Shenzhen City in China ; State Key Laboratory of Software Development Environment
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000452407300001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/3504]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Xingwu
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Beihang Univ, Engn Res Ctr ACAT, Minist Educ, Beijing 100191, Peoples R China 4.Beihang Univ, Res Inst, Shenzhen 518057, Peoples R China
推荐引用方式 GB/T 7714	Liu, Zhuang,Pu, Juhua,Liu, Xingwu,et al. MEMN:Multiple Vectors Embedding for Multi-Label Networks[J]. IEEE ACCESS,2018,6:66143-66152.
APA	Liu, Zhuang,Pu, Juhua,Liu, Xingwu,&Chen, Yujun.(2018).MEMN:Multiple Vectors Embedding for Multi-Label Networks.IEEE ACCESS,6,66143-66152.
MLA	Liu, Zhuang,et al."MEMN:Multiple Vectors Embedding for Multi-Label Networks".IEEE ACCESS 6(2018):66143-66152.