Sparse representation based spectral regression

Guo Xian Yu; Zhi Wen Yu; Jing Hua; Xuan Li; Jia You

doi:10.1109/ICMLC.2011.6016791

Sparse representation based spectral regression

Guo Xian Yu, Zhi Wen Yu, Jing Hua, Xuan Li, Jia You

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

3 Citations (Scopus)

Abstract

Spectral regression is a newly proposed method for dimensionality reduction, which is also based on graph embedding but less time and space consuming. However, like many methods based on neighborhood graphs, it still focuses on local manifold smoothness and ignores discriminative information among samples. In this paper, instead of making use of a neighborhood graph, we take advantage of a global graph defined by the coefficients of sparse representation and propose a method called Sparse Representation based Spectral Regression (SpSR) on this graph. This graph is data-driven, discriminative and robust to noise features. Experimental results on facial images feature extraction tasks demonstrate these advantages.

Original language	English
Title of host publication	Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011
Pages	532-537
Number of pages	6
Volume	2
DOIs	https://doi.org/10.1109/ICMLC.2011.6016791
Publication status	Published - 7 Nov 2011
Event	2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011 - Guilin, Guangxi, China Duration: 10 Jul 2011 → 13 Jul 2011

Conference

Conference	2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011
Country/Territory	China
City	Guilin, Guangxi
Period	10/07/11 → 13/07/11

Keywords

Discriminative
Neighborhood graph
Sparse representation
Spectral regression

ASJC Scopus subject areas

Artificial Intelligence
Computational Theory and Mathematics
Computer Networks and Communications
Human-Computer Interaction

More information

10.1109/ICMLC.2011.6016791

Cite this

@inproceedings{40b8f82f95874eed881ec7edf0cd5682,

title = "Sparse representation based spectral regression",

abstract = "Spectral regression is a newly proposed method for dimensionality reduction, which is also based on graph embedding but less time and space consuming. However, like many methods based on neighborhood graphs, it still focuses on local manifold smoothness and ignores discriminative information among samples. In this paper, instead of making use of a neighborhood graph, we take advantage of a global graph defined by the coefficients of sparse representation and propose a method called Sparse Representation based Spectral Regression (SpSR) on this graph. This graph is data-driven, discriminative and robust to noise features. Experimental results on facial images feature extraction tasks demonstrate these advantages.",

keywords = "Discriminative, Neighborhood graph, Sparse representation, Spectral regression",

author = "Yu, {Guo Xian} and Yu, {Zhi Wen} and Jing Hua and Xuan Li and Jia You",

year = "2011",

month = nov,

day = "7",

doi = "10.1109/ICMLC.2011.6016791",

language = "English",

isbn = "9781457703065",

volume = "2",

pages = "532--537",

booktitle = "Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011",

note = "2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011 ; Conference date: 10-07-2011 Through 13-07-2011",

}

Yu, GX, Yu, ZW, Hua, J, Li, X & You, J 2011, Sparse representation based spectral regression. in Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011. vol. 2, 6016791, pp. 532-537, 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011, Guilin, Guangxi, China, 10/07/11. https://doi.org/10.1109/ICMLC.2011.6016791

Sparse representation based spectral regression. / Yu, Guo Xian; Yu, Zhi Wen; Hua, Jing et al.
Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011. Vol. 2 2011. p. 532-537 6016791.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Sparse representation based spectral regression

AU - Yu, Guo Xian

AU - Yu, Zhi Wen

AU - Hua, Jing

AU - Li, Xuan

AU - You, Jia

PY - 2011/11/7

Y1 - 2011/11/7

N2 - Spectral regression is a newly proposed method for dimensionality reduction, which is also based on graph embedding but less time and space consuming. However, like many methods based on neighborhood graphs, it still focuses on local manifold smoothness and ignores discriminative information among samples. In this paper, instead of making use of a neighborhood graph, we take advantage of a global graph defined by the coefficients of sparse representation and propose a method called Sparse Representation based Spectral Regression (SpSR) on this graph. This graph is data-driven, discriminative and robust to noise features. Experimental results on facial images feature extraction tasks demonstrate these advantages.

AB - Spectral regression is a newly proposed method for dimensionality reduction, which is also based on graph embedding but less time and space consuming. However, like many methods based on neighborhood graphs, it still focuses on local manifold smoothness and ignores discriminative information among samples. In this paper, instead of making use of a neighborhood graph, we take advantage of a global graph defined by the coefficients of sparse representation and propose a method called Sparse Representation based Spectral Regression (SpSR) on this graph. This graph is data-driven, discriminative and robust to noise features. Experimental results on facial images feature extraction tasks demonstrate these advantages.

KW - Discriminative

KW - Neighborhood graph

KW - Sparse representation

KW - Spectral regression

UR - http://www.scopus.com/inward/record.url?scp=80155134968&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2011.6016791

DO - 10.1109/ICMLC.2011.6016791

M3 - Conference article published in proceeding or book

SN - 9781457703065

VL - 2

SP - 532

EP - 537

BT - Proceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011

T2 - 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011

Y2 - 10 July 2011 through 13 July 2011

ER -

Sparse representation based spectral regression

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this