Applying Ricci flow to high dimensional manifold learning

doi:10.1007/s11432-018-9702-7

CSpace > 数学所

	Applying Ricci flow to high dimensional manifold learning
	Li, Yangyang 1,2; Lu, Ruqian1
	2019-09-01
发表期刊	SCIENCE CHINA-INFORMATION SCIENCES
ISSN	1674-733X
卷号	62 期号:9 页码:14
摘要	In machine learning, a high dimensional data set such as the digital image of a human face is often viewed as a point set distributed on a differentiable manifold. In many cases, the intrinsic dimension of this manifold is low but the representation dimension of the data points is high. To ease data processing requirements, manifold learning (ML) techniques can be used to reduce a high dimensional manifold (HDM) to a low dimensional one while keeping the essential geometric properties, such as relative distances between points, unchanged. Traditional ML algorithms often assume that the local neighborhood of any point on an HDM is roughly equal to the tangent space at that point. This assumption leads to the disadvantage that the neighborhoods of points on the manifold, though they have a very different curvature, will be treated equally and will be projected to a lower dimensional space. The curvature is a different way of manifold processing, where traditional dimension reduction is ineffective at preserving the neighborhood. To overcome this obstacle, we perform an operation on the HDM using Ricci flow before a manifold's dimension reduction. More precisely, with the Ricci flow, we transform each local neighborhood of the HDM to a constant curvature patch. The HDM, as a whole, is then transformed into a subset of a sphere with constant positive curvature. We compare the proposed algorithm with other traditional manifold learning algorithms. Experimental results have shown that the proposed method outperforms other ML algorithms with a better neighborhood preserving rate.
关键词	manifold learning Ricci flow Ricci curvature dimension reduction curvature estimation
DOI	10.1007/s11432-018-9702-7
语种	英语
资助项目	National Key Research and Development Program of China[2016YFB1000902] ; National Natural Science Foundation of China[61472412] ; National Natural Science Foundation of China[61621003] ; Beijing Science and Technology Project ; Tsinghua-Tencent-AMSS-Joint Project
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:000468214300001
出版者	SCIENCE PRESS
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/34779
专题	数学所
通讯作者	Li, Yangyang
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Key Lab Management Decis & Informat Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Li, Yangyang,Lu, Ruqian. Applying Ricci flow to high dimensional manifold learning[J]. SCIENCE CHINA-INFORMATION SCIENCES,2019,62(9):14.
APA	Li, Yangyang,&Lu, Ruqian.(2019).Applying Ricci flow to high dimensional manifold learning.SCIENCE CHINA-INFORMATION SCIENCES,62(9),14.
MLA	Li, Yangyang,et al."Applying Ricci flow to high dimensional manifold learning".SCIENCE CHINA-INFORMATION SCIENCES 62.9(2019):14.