Designing a novel linear-time graph kernel for semantic link network

doi:10.1002/cpe.3541

	Designing a novel linear-time graph kernel for semantic link network
	Peng, Li 1; Zhang, Zhiying 1; Huang, Qiaoli 1; Huang, Zhixing 1; Hai Zhuge 1,2,3
	2015-10-01
发表期刊	CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
ISSN	1532-0626
卷号	27 期号:15 页码:4039-4052
摘要	Graph is an efficient tool for representing structured data such as proteins, molecular compounds, and social networks. Graph kernel is a technique to measure the similarity between graphs. However, existing graph kernels still have several limitations: (1) semantics on link is ignored; (2) node is associated with single label; (3) most graph kernels require more than cubic time, which is still computationally expensive; and, (4) there is seldom consideration of handling the graph comparison when the number of node types becomes huge. In this paper, we utilize semantic link network (SLN) to represent complex structured data with richer semantic information. Topic model is employed for dimension reduction and tagging each node with multiple labels. And a novel linear-time graph kernel for SLN is designed to calculate the similarity between two SLNs. This work remedies the limitations of the conventional graph kernels. The effectiveness and efficiency of this approach are evaluated by the document classification task on public corpora. Empirical results demonstrate that the proposed method can achieve better performance than the traditional topicmodel-based classification approach. Copyright (C) 2015 John Wiley & Sons, Ltd.
关键词	semantic link network latent Dirichlet allocation neighborhood hash graph kernel
DOI	10.1002/cpe.3541
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation Project of CQ CSTC[CSTC2012JJB40012] ; Fundamental Research Funds for the Central Universities[SWU1309265] ; Fundamental Research Funds for the Central Universities[XDJK2014B012]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:000363042100015
出版者	WILEY-BLACKWELL
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/9217
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Huang, Zhixing
作者单位	1.Southwest Univ, Sch Comp & Informat Sci, Semant Grid Lab, Chongqing 400715, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Nanjing Univ Posts & Telecommun, Nanjing 210003, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Peng, Li,Zhang, Zhiying,Huang, Qiaoli,et al. Designing a novel linear-time graph kernel for semantic link network[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE,2015,27(15):4039-4052.
APA	Peng, Li,Zhang, Zhiying,Huang, Qiaoli,Huang, Zhixing,&Hai Zhuge.(2015).Designing a novel linear-time graph kernel for semantic link network.CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE,27(15),4039-4052.
MLA	Peng, Li,et al."Designing a novel linear-time graph kernel for semantic link network".CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 27.15(2015):4039-4052.