Algorithms of Unconstrained Non-Negative Latent Factor Analysis for Recommender Systems

doi:10.1109/TBDATA.2019.2916868

	Algorithms of Unconstrained Non-Negative Latent Factor Analysis for Recommender Systems
	Luo, Xin 2,3,4; Zhou, Mengchu 1; Li, Shuai 5; Wu, Di 3,4; Liu, Zhigang 3,4; Shang, Mingsheng 3,4
刊名	IEEE TRANSACTIONS ON BIG DATA
	2021-03-01
卷号	7 期号:1 页码:227-240
关键词	Data models Training Sparse matrices Recommender systems Computational modeling Big Data Scalability Non-negative latent factor analysis non-negativity latent factor analysis unconstrained optimization high-dimensional and sparse matrix collaborative filtering recommender system big data
ISSN号	2332-7790
DOI	10.1109/TBDATA.2019.2916868
通讯作者	Luo, Xin(luoxin21@gmail.com) ; Shang, Mingsheng(msshang@cigit.ac.cn)
英文摘要	Non-negativity is vital for a latent factor (LF)-based model to preserve the important feature of a high-dimensional and sparse (HiDS) matrix in recommender systems, i.e., none of its entries is negative. Current non-negative models rely on constraints-combined training schemes. However, they lack flexibility, scalability, or compatibility with general training schemes. This work aims to perform unconstrained non-negative latent factor analysis (UNLFA) on HiDS matrices. To do so, we innovatively transfer the non-negativity constraints from the decision parameters to the output LFs, and connect them through a single-element-dependent mapping function. Then we theoretically prove that by making a mapping function fulfill specific conditions, the resultant model is able to represent the original one precisely. We subsequently design highly efficient UNLFA algorithms for recommender systems. Experimental results on four industrial-size HiDS matrices demonstrate that compared with four state-of-the-art non-negative models, a UNLFA-based model obtains advantage in prediction accuracy for missing data and computational efficiency. Moreover, such high performance is achieved through its unconstrained training process which is compatible with various general training schemes, on the premise of fulfilling non-negativity constraints. Hence, UNLFA algorithms are highly valuable for industrial applications with the need of performing non-negative latent factor analysis on HiDS matrices.
资助项目	National Natural Science Foundation of China[61772493] ; National Natural Science Foundation of China[91646114] ; National Key Research and Development Program of China[2017YFC0804002] ; Chongqing Research Program of Technology Innovation and Application[cstc2017rgzn-zdyfX0020] ; Chongqing Research Program of Technology Innovation and Application[cstc2017zdcy-zdyf0554] ; Chongqing Research Program of Technology Innovation and Application[cstc2017rgzn-zdyf0118] ; Chongqing Cultivation Program of Innovation and Entrepreneurship Demonstration Group[cstc2017kjrc-cxcytd0149] ; Chongqing Overseas Scholars Innovation Program[cx2017012] ; Chongqing Overseas Scholars Innovation Program[cx2018011] ; Pioneer Hundred Talents Program of Chinese Academy of Sciences
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000626322200018
内容类型	期刊论文
源URL	[http://119.78.100.138/handle/2HOD01W0/13255]
专题	中国科学院重庆绿色智能技术研究院
通讯作者	Luo, Xin; Shang, Mingsheng
作者单位	1.New Jersey Inst Technol, Dept Elect & Comp Engn, Newark, NJ 07102 USA 2.Dongguan Univ Technol, Sch Comp Sci & Technol, Dongguan 523808, Guangdong, Peoples R China 3.Chinese Acad Sci, Chongqing Engn Res Ctr Big Data Applicat Smart Ci, Chongqing 400714, Peoples R China 4.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Big Data & Intelligent Comp, Chongqing 400714, Peoples R China 5.Hong Kong Polytech Univ, Dept Comp, Hong Kong 999077, Peoples R China
推荐引用方式 GB/T 7714	Luo, Xin,Zhou, Mengchu,Li, Shuai,et al. Algorithms of Unconstrained Non-Negative Latent Factor Analysis for Recommender Systems[J]. IEEE TRANSACTIONS ON BIG DATA,2021,7(1):227-240.
APA	Luo, Xin,Zhou, Mengchu,Li, Shuai,Wu, Di,Liu, Zhigang,&Shang, Mingsheng.(2021).Algorithms of Unconstrained Non-Negative Latent Factor Analysis for Recommender Systems.IEEE TRANSACTIONS ON BIG DATA,7(1),227-240.
MLA	Luo, Xin,et al."Algorithms of Unconstrained Non-Negative Latent Factor Analysis for Recommender Systems".IEEE TRANSACTIONS ON BIG DATA 7.1(2021):227-240.