中文版 | English
CSpace
Non-Negativity Constrained Missing Data Estimation for High-Dimensional and Sparse Matrices from Industrial Applications
Luo, Xin1,2,3; Zhou, MengChu4,5; Li, Shuai6; Hu, Lun7; Shang, Mingsheng2,3
2020-05-01
摘要High-dimensional and sparse (HiDS) matrices are commonly seen in big-data-related industrial applications like recommender systems. Latent factor (LF) models have proven to be accurate and efficient in extracting hidden knowledge from them. However, they mostly fail to fulfill the non-negativity constraints that describe the non-negative nature of many industrial data. Moreover, existing models suffer from slow convergence rate. An alternating-direction-method of multipliers-based non-negative LF (AMNLF) model decomposes the task of non-negative LF analysis on an HiDS matrix into small subtasks, where each task is solved based on the latest solutions to the previously solved ones, thereby achieving fast convergence and high prediction accuracy for its missing data. This paper theoretically analyzes the characteristics of an AMNLF model, and presents detailed empirical studies regarding its performance on nine HiDS matrices from industrial applications currently in use. Therefore, its capability of addressing HiDS matrices is justified in both theory and practice.
关键词Computational modeling Data models Sparse matrices Linear programming Training Convergence Analytical models Alternating-direction-method of multipliers high-dimensional and sparse matrix industrial application non-negative latent factor analysis recommender system
DOI10.1109/TCYB.2019.2894283
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
ISSN2168-2267
卷号50期号:5页码:1844-1855
通讯作者Luo, Xin(luoxin21@dgut.edu.cn) ; Zhou, MengChu(zhou@njit.edu)
收录类别SCI
WOS记录号WOS:000528622000006
语种英语