skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Incremental nonnegative matrix factorization based on correlation and graph regularization for matrix completion

Abstract

Matrix factorization is widely used in recommendation systems, text mining, face recognition and computer vision. As one of the most popular methods, nonnegative matrix factorization and its incremental variants have attracted much attention. The existing incremental algorithms are established based on the assumption of samples are independent and only update the new latent variable of weighting coefficient matrix when the new sample comes, which may lead to inferior solutions. To address this issue, we investigate a novel incremental nonnegative matrix factorization algorithm based on correlation and graph regularizer (ICGNMF). The correlation is mainly used for finding out those correlated rows to be updated, that is, we assume that samples are dependent on each other. We derive the updating rules for ICGNMF by considering the correlation. We also present tests on widely used image datasets, and show ICGNMF reduces the error by comparing other methods.

Authors:
ORCiD logo [1];  [2];  [3]
  1. North China Electric Power Univ., Beijing (China). School of Control and Computer Engineering; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division
  2. North China Electric Power Univ., Beijing (China). Dept. of Mathematics and Physics
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory-National Energy Research Scientific Computing Center (NERSC)
Sponsoring Org.:
USDOE
OSTI Identifier:
1526987
Resource Type:
Journal Article
Journal Name:
International Journal of Machine Learning and Cybernetics
Additional Journal Information:
Journal Volume: 10; Journal Issue: 6; Journal ID: ISSN 1868-8071
Country of Publication:
United States
Language:
English

Citation Formats

Zhang, Xiaoxia, Chen, Degang, and Wu, Kesheng. Incremental nonnegative matrix factorization based on correlation and graph regularization for matrix completion. United States: N. p., 2018. Web. doi:10.1007/s13042-018-0808-7.
Zhang, Xiaoxia, Chen, Degang, & Wu, Kesheng. Incremental nonnegative matrix factorization based on correlation and graph regularization for matrix completion. United States. doi:10.1007/s13042-018-0808-7.
Zhang, Xiaoxia, Chen, Degang, and Wu, Kesheng. Thu . "Incremental nonnegative matrix factorization based on correlation and graph regularization for matrix completion". United States. doi:10.1007/s13042-018-0808-7.
@article{osti_1526987,
title = {Incremental nonnegative matrix factorization based on correlation and graph regularization for matrix completion},
author = {Zhang, Xiaoxia and Chen, Degang and Wu, Kesheng},
abstractNote = {Matrix factorization is widely used in recommendation systems, text mining, face recognition and computer vision. As one of the most popular methods, nonnegative matrix factorization and its incremental variants have attracted much attention. The existing incremental algorithms are established based on the assumption of samples are independent and only update the new latent variable of weighting coefficient matrix when the new sample comes, which may lead to inferior solutions. To address this issue, we investigate a novel incremental nonnegative matrix factorization algorithm based on correlation and graph regularizer (ICGNMF). The correlation is mainly used for finding out those correlated rows to be updated, that is, we assume that samples are dependent on each other. We derive the updating rules for ICGNMF by considering the correlation. We also present tests on widely used image datasets, and show ICGNMF reduces the error by comparing other methods.},
doi = {10.1007/s13042-018-0808-7},
journal = {International Journal of Machine Learning and Cybernetics},
issn = {1868-8071},
number = 6,
volume = 10,
place = {United States},
year = {2018},
month = {3}
}

Works referenced in this record:

A non negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic model
journal, April 2016


Learning the parts of objects by non-negative matrix factorization
journal, October 1999

  • Lee, Daniel D.; Seung, H. Sebastian
  • Nature, Vol. 401, Issue 6755
  • DOI: 10.1038/44565

Inferential, robust non-negative matrix factorization analysis of microarray data
journal, November 2006


Graph Regularized Nonnegative Matrix Factorization for Data Representation
journal, August 2011

  • Deng Cai,
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, Issue 8
  • DOI: 10.1109/TPAMI.2010.231

Convex and Semi-Nonnegative Matrix Factorizations
journal, January 2010

  • Ding, C. H. Q.; Jordan, M. I.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, Issue 1
  • DOI: 10.1109/TPAMI.2008.277

Online Nonnegative Matrix Factorization With Robust Stochastic Approximation
journal, July 2012


An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems
journal, May 2014


Predicting Quality of Service for Selection by Neighborhood-Based Collaborative Filtering
journal, March 2013

  • Wu, Jian; Chen, Liang; Feng, Yipeng
  • IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 43, Issue 2
  • DOI: 10.1109/TSMCA.2012.2210409

Incremental subspace learning via non-negative matrix factorization
journal, May 2009


Online Blind Source Separation Using Incremental Nonnegative Matrix Factorization With Volume Constraint
journal, April 2011


A Global Geometric Framework for Nonlinear Dimensionality Reduction
journal, December 2000


Nonlinear Dimensionality Reduction by Locally Linear Embedding
journal, December 2000