Home > Research > Publications & Outputs > A Novel Correlation-Based CUR Matrix Decomposit...

Research

Text available via DOI:

Keywords

View graph of relations

A Novel Correlation-Based CUR Matrix Decomposition Method

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

A Novel Correlation-Based CUR Matrix Decomposition Method. / Hemmati, Arash; Nasiri, Hamid; Haeri, Maryam Amir et al.
2020 6th International Conference on Web Research, ICWR 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 172-176 9122286 (2020 6th International Conference on Web Research, ICWR 2020).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Hemmati, A, Nasiri, H, Haeri, MA & Ebadzadeh, MM 2020, A Novel Correlation-Based CUR Matrix Decomposition Method. in 2020 6th International Conference on Web Research, ICWR 2020., 9122286, 2020 6th International Conference on Web Research, ICWR 2020, Institute of Electrical and Electronics Engineers Inc., pp. 172-176, 6th International Conference on Web Research, ICWR 2020, Tehran, Iran, Islamic Republic of, 22/04/20. https://doi.org/10.1109/ICWR49608.2020.9122286

APA

Hemmati, A., Nasiri, H., Haeri, M. A., & Ebadzadeh, M. M. (2020). A Novel Correlation-Based CUR Matrix Decomposition Method. In 2020 6th International Conference on Web Research, ICWR 2020 (pp. 172-176). Article 9122286 (2020 6th International Conference on Web Research, ICWR 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICWR49608.2020.9122286

Vancouver

Hemmati A, Nasiri H, Haeri MA, Ebadzadeh MM. A Novel Correlation-Based CUR Matrix Decomposition Method. In 2020 6th International Conference on Web Research, ICWR 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 172-176. 9122286. (2020 6th International Conference on Web Research, ICWR 2020). doi: 10.1109/ICWR49608.2020.9122286

Author

Hemmati, Arash ; Nasiri, Hamid ; Haeri, Maryam Amir et al. / A Novel Correlation-Based CUR Matrix Decomposition Method. 2020 6th International Conference on Web Research, ICWR 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 172-176 (2020 6th International Conference on Web Research, ICWR 2020).

Bibtex

@inproceedings{13c475050f314c2c933ec455b4b7db10,
title = "A Novel Correlation-Based CUR Matrix Decomposition Method",
abstract = "Web data such as documents, images, and videos are examples of large matrices. To deal with such matrices, one may use matrix decomposition techniques. As such, CUR matrix decomposition is an important approximation technique for high-dimensional data. It approximates a data matrix by selecting a few of its rows and columns. However, a problem faced by most CUR decomposition matrix methods is that they ignore the correlation among columns (rows), which gives them lesser chance to be selected; even though, they might be appropriate candidates for basis vectors. In this paper, a novel CUR matrix decomposition method is proposed, in which calculation of the correlation, boosts the chance of selecting such columns (rows). Experimental results indicate that in comparison with other methods, this one has had higher accuracy in matrix approximation.",
keywords = "CUR Matrix Decomposition, High-Dimensional Data, Low-Rank Approximations, Singular Value Decomposition",
author = "Arash Hemmati and Hamid Nasiri and Haeri, {Maryam Amir} and Ebadzadeh, {Mohammad Mehdi}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 6th International Conference on Web Research, ICWR 2020 ; Conference date: 22-04-2020 Through 23-04-2020",
year = "2020",
month = apr,
doi = "10.1109/ICWR49608.2020.9122286",
language = "English",
series = "2020 6th International Conference on Web Research, ICWR 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "172--176",
booktitle = "2020 6th International Conference on Web Research, ICWR 2020",

}

RIS

TY - GEN

T1 - A Novel Correlation-Based CUR Matrix Decomposition Method

AU - Hemmati, Arash

AU - Nasiri, Hamid

AU - Haeri, Maryam Amir

AU - Ebadzadeh, Mohammad Mehdi

N1 - Publisher Copyright: © 2020 IEEE.

PY - 2020/4

Y1 - 2020/4

N2 - Web data such as documents, images, and videos are examples of large matrices. To deal with such matrices, one may use matrix decomposition techniques. As such, CUR matrix decomposition is an important approximation technique for high-dimensional data. It approximates a data matrix by selecting a few of its rows and columns. However, a problem faced by most CUR decomposition matrix methods is that they ignore the correlation among columns (rows), which gives them lesser chance to be selected; even though, they might be appropriate candidates for basis vectors. In this paper, a novel CUR matrix decomposition method is proposed, in which calculation of the correlation, boosts the chance of selecting such columns (rows). Experimental results indicate that in comparison with other methods, this one has had higher accuracy in matrix approximation.

AB - Web data such as documents, images, and videos are examples of large matrices. To deal with such matrices, one may use matrix decomposition techniques. As such, CUR matrix decomposition is an important approximation technique for high-dimensional data. It approximates a data matrix by selecting a few of its rows and columns. However, a problem faced by most CUR decomposition matrix methods is that they ignore the correlation among columns (rows), which gives them lesser chance to be selected; even though, they might be appropriate candidates for basis vectors. In this paper, a novel CUR matrix decomposition method is proposed, in which calculation of the correlation, boosts the chance of selecting such columns (rows). Experimental results indicate that in comparison with other methods, this one has had higher accuracy in matrix approximation.

KW - CUR Matrix Decomposition

KW - High-Dimensional Data

KW - Low-Rank Approximations

KW - Singular Value Decomposition

U2 - 10.1109/ICWR49608.2020.9122286

DO - 10.1109/ICWR49608.2020.9122286

M3 - Conference contribution/Paper

AN - SCOPUS:85089172954

T3 - 2020 6th International Conference on Web Research, ICWR 2020

SP - 172

EP - 176

BT - 2020 6th International Conference on Web Research, ICWR 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Web Research, ICWR 2020

Y2 - 22 April 2020 through 23 April 2020

ER -