NNNPE: non-neighbourhood and neighbourhood preserving embedding

Manifold learning is an important class of methods for nonlinear dimensionality reduction. Among them, the LLE optimisation goal is to maintain the relationship between local neighbourhoods in the original embedding manifold to reduce dimensionality, and NPE is a linear approximation to LLE. However...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaizhi Chen, Chengpei Le, Shangping Zhong, Longkun Guo, Ge Xu
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2022.2133082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850236231667941376
author Kaizhi Chen
Chengpei Le
Shangping Zhong
Longkun Guo
Ge Xu
author_facet Kaizhi Chen
Chengpei Le
Shangping Zhong
Longkun Guo
Ge Xu
author_sort Kaizhi Chen
collection DOAJ
description Manifold learning is an important class of methods for nonlinear dimensionality reduction. Among them, the LLE optimisation goal is to maintain the relationship between local neighbourhoods in the original embedding manifold to reduce dimensionality, and NPE is a linear approximation to LLE. However, these two algorithms only consider maintaining the neighbour relationship of samples in low-dimensional space and ignore the global features between non-neighbour samples, such as the face shooting angle. Therefore, in order to simultaneously consider the nearest neighbour structure and global features of samples in nonlinear dimensionality reduction, it can be linearly calculated. This work provides a novel linear dimensionality reduction approach named non-neighbour and neighbour preserving embedding (NNNPE). First, we rewrite the objective function of the algorithm LLE based on the principle of our novel algorithm. Second, we introduce the linear mapping to the objective function. Finally, the mapping matrix is calculated by the method of the fast learning Mahalanobis metric. The experimental results show that the method proposed in this paper is effective.
format Article
id doaj-art-151e4b568f644de6a9b68eada2f560ee
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-151e4b568f644de6a9b68eada2f560ee2025-08-20T02:02:01ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013412615262910.1080/09540091.2022.21330822133082NNNPE: non-neighbourhood and neighbourhood preserving embeddingKaizhi Chen0Chengpei Le1Shangping Zhong2Longkun Guo3Ge Xu4College of Computer and Data Science, Fuzhou UniversityCollege of Computer and Data Science, Fuzhou UniversityCollege of Computer and Data Science, Fuzhou UniversityCollege of Computer and Data Science, Fuzhou UniversityMinjiang UniversityManifold learning is an important class of methods for nonlinear dimensionality reduction. Among them, the LLE optimisation goal is to maintain the relationship between local neighbourhoods in the original embedding manifold to reduce dimensionality, and NPE is a linear approximation to LLE. However, these two algorithms only consider maintaining the neighbour relationship of samples in low-dimensional space and ignore the global features between non-neighbour samples, such as the face shooting angle. Therefore, in order to simultaneously consider the nearest neighbour structure and global features of samples in nonlinear dimensionality reduction, it can be linearly calculated. This work provides a novel linear dimensionality reduction approach named non-neighbour and neighbour preserving embedding (NNNPE). First, we rewrite the objective function of the algorithm LLE based on the principle of our novel algorithm. Second, we introduce the linear mapping to the objective function. Finally, the mapping matrix is calculated by the method of the fast learning Mahalanobis metric. The experimental results show that the method proposed in this paper is effective.http://dx.doi.org/10.1080/09540091.2022.2133082machine learningmanifold learningdimensionality reductionneighborhood preserving embedding
spellingShingle Kaizhi Chen
Chengpei Le
Shangping Zhong
Longkun Guo
Ge Xu
NNNPE: non-neighbourhood and neighbourhood preserving embedding
Connection Science
machine learning
manifold learning
dimensionality reduction
neighborhood preserving embedding
title NNNPE: non-neighbourhood and neighbourhood preserving embedding
title_full NNNPE: non-neighbourhood and neighbourhood preserving embedding
title_fullStr NNNPE: non-neighbourhood and neighbourhood preserving embedding
title_full_unstemmed NNNPE: non-neighbourhood and neighbourhood preserving embedding
title_short NNNPE: non-neighbourhood and neighbourhood preserving embedding
title_sort nnnpe non neighbourhood and neighbourhood preserving embedding
topic machine learning
manifold learning
dimensionality reduction
neighborhood preserving embedding
url http://dx.doi.org/10.1080/09540091.2022.2133082
work_keys_str_mv AT kaizhichen nnnpenonneighbourhoodandneighbourhoodpreservingembedding
AT chengpeile nnnpenonneighbourhoodandneighbourhoodpreservingembedding
AT shangpingzhong nnnpenonneighbourhoodandneighbourhoodpreservingembedding
AT longkunguo nnnpenonneighbourhoodandneighbourhoodpreservingembedding
AT gexu nnnpenonneighbourhoodandneighbourhoodpreservingembedding