A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems

Jiufang Chen; Xin Luo; Meng Chu Zhou

doi:10.1109/ICHMS49158.2020.9209550

A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems

Jiufang Chen, Xin Luo, Meng Chu Zhou

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-Adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-Adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.

Original language	English (US)
Title of host publication	Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020
Editors	Giancarlo Fortino, Fei-Yue Wang, Andreas Nurnberger, David Kaber, Rino Falcone, David Mendonca, Zhiwen Yu, Antonio Guerrieri
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728158716
DOIs	https://doi.org/10.1109/ICHMS49158.2020.9209550
State	Published - Sep 2020
Event	1st IEEE International Conference on Human-Machine Systems, ICHMS 2020 - Virtual, Rome, Italy Duration: Sep 7 2020 → Sep 9 2020

Publication series

Name	Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020

Conference

Conference	1st IEEE International Conference on Human-Machine Systems, ICHMS 2020
Country/Territory	Italy
City	Virtual, Rome
Period	9/7/20 → 9/9/20

All Science Journal Classification (ASJC) codes

Human-Computer Interaction

Keywords

High-Dimensional and Sparse Matrix
Non-negative Latent Factor Analysis
Particle Swarm Optimization
Recommender System
Self-Adaptive Model

Access to Document

10.1109/ICHMS49158.2020.9209550

Cite this

Chen, J., Luo, X., & Zhou, M. C. (2020). A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems. In G. Fortino, F-Y. Wang, A. Nurnberger, D. Kaber, R. Falcone, D. Mendonca, Z. Yu, & A. Guerrieri (Eds.), Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020 Article 9209550 (Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHMS49158.2020.9209550

Chen, Jiufang ; Luo, Xin ; Zhou, Meng Chu. / A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems. Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020. editor / Giancarlo Fortino ; Fei-Yue Wang ; Andreas Nurnberger ; David Kaber ; Rino Falcone ; David Mendonca ; Zhiwen Yu ; Antonio Guerrieri. Institute of Electrical and Electronics Engineers Inc., 2020. (Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020).

@inproceedings{cc1c59e70d2e4eb8bc822fd14c0bbe84,

title = "A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems",

abstract = "Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-Adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-Adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.",

keywords = "High-Dimensional and Sparse Matrix, Non-negative Latent Factor Analysis, Particle Swarm Optimization, Recommender System, Self-Adaptive Model",

author = "Jiufang Chen and Xin Luo and Zhou, {Meng Chu}",

note = "Funding Information: This research is supported in part by the National Natural Science Foundation of China under grants 61772493, 91646114 and 61602352, in part by the Natural Science Foundation of Chongqing (China) under grants cstc2019jcyjjqX0013, and in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciences. X. Luo and J. Chen are co-first authors of this paper (Corresponding Author: X. Luo). Publisher Copyright: {\textcopyright} 2020 IEEE.; 1st IEEE International Conference on Human-Machine Systems, ICHMS 2020 ; Conference date: 07-09-2020 Through 09-09-2020",

year = "2020",

month = sep,

doi = "10.1109/ICHMS49158.2020.9209550",

language = "English (US)",

series = "Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Giancarlo Fortino and Fei-Yue Wang and Andreas Nurnberger and David Kaber and Rino Falcone and David Mendonca and Zhiwen Yu and Antonio Guerrieri",

booktitle = "Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020",

address = "United States",

}

Chen, J, Luo, X & Zhou, MC 2020, A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems. in G Fortino, F-Y Wang, A Nurnberger, D Kaber, R Falcone, D Mendonca, Z Yu & A Guerrieri (eds), Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020., 9209550, Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020, Institute of Electrical and Electronics Engineers Inc., 1st IEEE International Conference on Human-Machine Systems, ICHMS 2020, Virtual, Rome, Italy, 9/7/20. https://doi.org/10.1109/ICHMS49158.2020.9209550

A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems. / Chen, Jiufang; Luo, Xin; Zhou, Meng Chu.
Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020. ed. / Giancarlo Fortino; Fei-Yue Wang; Andreas Nurnberger; David Kaber; Rino Falcone; David Mendonca; Zhiwen Yu; Antonio Guerrieri. Institute of Electrical and Electronics Engineers Inc., 2020. 9209550 (Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems

AU - Chen, Jiufang

AU - Luo, Xin

AU - Zhou, Meng Chu

N1 - Funding Information: This research is supported in part by the National Natural Science Foundation of China under grants 61772493, 91646114 and 61602352, in part by the Natural Science Foundation of Chongqing (China) under grants cstc2019jcyjjqX0013, and in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciences. X. Luo and J. Chen are co-first authors of this paper (Corresponding Author: X. Luo). Publisher Copyright: © 2020 IEEE.

PY - 2020/9

Y1 - 2020/9

N2 - Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-Adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-Adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.

AB - Non-negative latent factor analysis (NLFA) can high-efficiently extract useful information from high dimensional and sparse (HiDS) matrices often encountered in recommender systems (RSs). However, an NLFA-based model requires careful tuning of regularization coefficients, which is highly expensive in both time and computation. To address this issue, this study proposes an adaptive NLFA-based model whose regularization coefficients become self-Adaptive via particle swarm optimization. Experimental results on two HiDS matrices indicate that owing to such self-Adaptation, it outperforms an NLFA model in terms of both convergence rate and prediction accuracy for missing data estimation.

KW - High-Dimensional and Sparse Matrix

KW - Non-negative Latent Factor Analysis

KW - Particle Swarm Optimization

KW - Recommender System

KW - Self-Adaptive Model

UR - http://www.scopus.com/inward/record.url?scp=85093982328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85093982328&partnerID=8YFLogxK

U2 - 10.1109/ICHMS49158.2020.9209550

DO - 10.1109/ICHMS49158.2020.9209550

M3 - Conference contribution

AN - SCOPUS:85093982328

T3 - Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020

BT - Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020

A2 - Fortino, Giancarlo

A2 - Wang, Fei-Yue

A2 - Nurnberger, Andreas

A2 - Kaber, David

A2 - Falcone, Rino

A2 - Mendonca, David

A2 - Yu, Zhiwen

A2 - Guerrieri, Antonio

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st IEEE International Conference on Human-Machine Systems, ICHMS 2020

Y2 - 7 September 2020 through 9 September 2020

ER -

Chen J, Luo X, Zhou MC. A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems. In Fortino G, Wang F-Y, Nurnberger A, Kaber D, Falcone R, Mendonca D, Yu Z, Guerrieri A, editors, Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9209550. (Proceedings of the 2020 IEEE International Conference on Human-Machine Systems, ICHMS 2020). doi: 10.1109/ICHMS49158.2020.9209550

A Regularization-Adaptive Non-negative Latent Factor Analysis-based Model for Recommender Systems

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this