Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data

Yi Guo; Junbin Gao; Paul W. Kwan

doi:10.1007/978-3-642-10439-8_25

Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data

Yi Guo, Junbin Gao, Paul W. Kwan

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

In this paper, we proposed a new nonlinear dimensionality reduction algorithm called regularized Kernel Local Linear Embedding (rKLLE) for highly structured data. It is built on the original LLE by introducing kernel alignment type of constraint to effectively reduce the solution space and find out the embeddings reflecting the prior knowledge. To enable the non-vectorial data applicability of the algorithm, a kernelized LLE is used to get the reconstruction weights. Our experiments on typical non-vectorial data show that rKLLE greatly improves the results of KLLE.

Original language	English
Title of host publication	Proceedings AI 2009: Advances in Artificial Intelligence: 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009
Publisher	Springer
Pages	240-249
Number of pages	10
ISBN (Print)	364210438X
DOIs	https://doi.org/10.1007/978-3-642-10439-8_25
Publication status	Published - 2009
Event	Australasian Joint Conference on Artificial Intelligence - Duration: 1 Dec 2013 → …

Publication series

Name
ISSN (Print)	0302-9743

Conference

Conference	Australasian Joint Conference on Artificial Intelligence
Period	1/12/13 → …

Keywords

algorithms
artificial intelligence
embeddings (mathematics)
kernel functions

Access to Document

10.1007/978-3-642-10439-8_25

Cite this

@inproceedings{1073beceb8114da78225d3cdde974f0e,

title = "Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data",

abstract = "In this paper, we proposed a new nonlinear dimensionality reduction algorithm called regularized Kernel Local Linear Embedding (rKLLE) for highly structured data. It is built on the original LLE by introducing kernel alignment type of constraint to effectively reduce the solution space and find out the embeddings reflecting the prior knowledge. To enable the non-vectorial data applicability of the algorithm, a kernelized LLE is used to get the reconstruction weights. Our experiments on typical non-vectorial data show that rKLLE greatly improves the results of KLLE.",

keywords = "algorithms, artificial intelligence, embeddings (mathematics), kernel functions",

author = "Yi Guo and Junbin Gao and Kwan, {Paul W.}",

year = "2009",

doi = "10.1007/978-3-642-10439-8_25",

language = "English",

isbn = "364210438X",

publisher = "Springer",

pages = "240--249",

booktitle = "Proceedings AI 2009: Advances in Artificial Intelligence: 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009",

note = "Australasian Joint Conference on Artificial Intelligence ; Conference date: 01-12-2013",

}

Guo, Y, Gao, J & Kwan, PW 2009, Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data. in Proceedings AI 2009: Advances in Artificial Intelligence: 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009. Springer, pp. 240-249, Australasian Joint Conference on Artificial Intelligence, 1/12/13. https://doi.org/10.1007/978-3-642-10439-8_25

Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data. / Guo, Yi; Gao, Junbin; Kwan, Paul W.
Proceedings AI 2009: Advances in Artificial Intelligence: 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009. Springer, 2009. p. 240-249.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data

AU - Guo, Yi

AU - Gao, Junbin

AU - Kwan, Paul W.

PY - 2009

Y1 - 2009

N2 - In this paper, we proposed a new nonlinear dimensionality reduction algorithm called regularized Kernel Local Linear Embedding (rKLLE) for highly structured data. It is built on the original LLE by introducing kernel alignment type of constraint to effectively reduce the solution space and find out the embeddings reflecting the prior knowledge. To enable the non-vectorial data applicability of the algorithm, a kernelized LLE is used to get the reconstruction weights. Our experiments on typical non-vectorial data show that rKLLE greatly improves the results of KLLE.

AB - In this paper, we proposed a new nonlinear dimensionality reduction algorithm called regularized Kernel Local Linear Embedding (rKLLE) for highly structured data. It is built on the original LLE by introducing kernel alignment type of constraint to effectively reduce the solution space and find out the embeddings reflecting the prior knowledge. To enable the non-vectorial data applicability of the algorithm, a kernelized LLE is used to get the reconstruction weights. Our experiments on typical non-vectorial data show that rKLLE greatly improves the results of KLLE.

KW - algorithms

KW - artificial intelligence

KW - embeddings (mathematics)

KW - kernel functions

UR - http://handle.uws.edu.au:8081/1959.7/uws:35070

U2 - 10.1007/978-3-642-10439-8_25

DO - 10.1007/978-3-642-10439-8_25

M3 - Conference Paper

SN - 364210438X

SP - 240

EP - 249

BT - Proceedings AI 2009: Advances in Artificial Intelligence: 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009

PB - Springer

T2 - Australasian Joint Conference on Artificial Intelligence

Y2 - 1 December 2013

ER -

Regularized Kernel Local Linear Embedding on dimensionality reduction for non-vectorial data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this