Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold

doi:10.1016/j.neucom.2015.02.023

	Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold
	Jia, Kui 1,2; Sun, Lin 3; Gao, Shenghua4 ; Song, Zhan 5; Shi, Bertram E.3
	2015-07-21
发表期刊	NEUROCOMPUTING (IF:5.5[JCR-2023],5.5[5-Year])
ISSN	0925-2312
卷号	160 页码:250-260
发表状态	已发表
DOI	10.1016/j.neucom.2015.02.023
摘要	A key factor contributing to the success of many auto-encoders based deep learning techniques is the implicit consideration of the underlying data manifold in their training criteria. In this paper, we aim to make this consideration more explicit by training auto-encoders completely from the manifold learning perspective. We propose a novel unsupervised manifold learning method termed Laplacian Auto-Encoders (LAEs). Starting from a general regularized function learning framework, LAE regularizes training of auto-encoders so that the learned encoding function has the locality-preserving property for data points on the manifold. By exploiting the analog relation between the graph Laplacian and the Laplace-Beltrami operator on the continuous manifold, we derive discrete approximations of the first- and higher-order auto-encoder regularizers that can be applied in practical scenarios, where only data points sampled from the distribution on the manifold are available. Our proposed LAE has potentially better generalization capability, due to its explicit respect of the underlying data manifold. Extensive experiments on benchmark visual classification datasets show that LAE consistently outperforms alternative auto-encoders recently proposed in deep learning literature, especially when training samples are relatively scarce: (C) 2015 Elsevier B.V. All rights reserved.
关键词	Auto-encoders Deep learning Manifold learning Image classification
收录类别	SCI ; EI
语种	英语
资助项目	National Natural Science Foundation of China[61202158]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000354139100022
出版者	ELSEVIER SCIENCE BV
EI入藏号	20151200672876
EI主题词	Classification (of information) ; Face recognition ; Image classification ; Laplace transforms
WOS关键词	DIMENSIONALITY REDUCTION ; IMAGE ; EIGENMAPS
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/2174
专题	信息科学与技术学院_PI研究组_高盛华组
通讯作者	Jia, Kui
作者单位	1.Univ Macau, Fac Sci & Technol, Dept Elect & Comp Engn, Macau, Peoples R China 2.Adv Digital Sci Ctr, Singapore 138632, Singapore 3.Hong Kong Univ Sci & Technol, Dept Elect & Comp Engn, Kowloon, Hong Kong, Peoples R China 4.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 5.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Jia, Kui,Sun, Lin,Gao, Shenghua,et al. Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold[J]. NEUROCOMPUTING,2015,160:250-260.
APA	Jia, Kui,Sun, Lin,Gao, Shenghua,Song, Zhan,&Shi, Bertram E..(2015).Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold.NEUROCOMPUTING,160,250-260.
MLA	Jia, Kui,et al."Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold".NEUROCOMPUTING 160(2015):250-260.