A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method
Document Type
Article
Publication Date
3-1-2016
Abstract
Nonnegative matrix factorization (NMF)-based models possess fine representativeness of a target matrix, which is critically important in collaborative filtering (CF)-based recommender systems. However, current NMF-based CF recommenders suffer from the problem of high computational and storage complexity, as well as slow convergence rate, which prevents them from industrial usage in context of big data. To address these issues, this paper proposes an alternating direction method (ADM)-based nonnegative latent factor (ANLF) model. The main idea is to implement the ADM-based optimization with regard to each single feature, to obtain high convergence rate as well as low complexity. Both computational and storage costs of ANLF are linear with the size of given data in the target matrix, which ensures high efficiency when dealing with extremely sparse matrices usually seen in CF problems. As demonstrated by the experiments on large, real data sets, ANLF also ensures fast convergence and high prediction accuracy, as well as the maintenance of nonnegativity constraints. Moreover, it is simple and easy to implement for real applications of learning systems.
Identifier
84929832189 (Scopus)
Publication Title
IEEE Transactions on Neural Networks and Learning Systems
External Full Text Location
https://doi.org/10.1109/TNNLS.2015.2415257
e-ISSN
21622388
ISSN
2162237X
First Page
579
Last Page
592
Issue
3
Volume
27
Grant
1162482
Fund Ref
National Science Foundation
Recommended Citation
Luo, Xin; Zhou, Meng Chu; Li, Shuai; You, Zhuhong; Xia, Yunni; and Zhu, Qingsheng, "A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method" (2016). Faculty Publications. 10664.
https://digitalcommons.njit.edu/fac_pubs/10664
