More Web Proxy on the site http://driver.im/

Article

Detect and track latent factors with online nonnegative matrix factorization

Authors:

Zheng ChenAuthors Info & Claims

IJCAI'07: Proceedings of the 20th international joint conference on Artifical intelligence

Pages 2689 - 2694

Published: 06 January 2007 Publication History

Abstract

Detecting and tracking latent factors from temporal data is an important task. Most existing algorithms for latent topic detection such as Nonnegative Matrix Factorization (NMF) have been designed for static data. These algorithms are unable to capture the dynamic nature of temporally changing data streams. In this paper, we put forward an online NMF (ONMF) algorithm to detect latent factors and track their evolution while the data evolve. By leveraging the already detected latent factors and the newly arriving data, the latent factors are automatically and incrementally updated to reflect the change of factors. Furthermore, by imposing orthogonality on the detected latent factors, we can not only guarantee the unique solution of NMF but also alleviate the partial-data problem, which may cause NMF to fail when the data are scarce or the distribution is incomplete. Experiments on both synthesized data and real data validate the efficiency and effectiveness of our ONMF algorithm.

References

[1]

C. Aggarwal, J. Han, J. Wang, and P. Yu. A framework for clustering evolving data streams. In Proc. of the 29th VLDB conference, 2003.

Digital Library

[2]

James Allan, Jaime Carbonell, George Doddington, Jonathan Yamron, and Yiming Yang. Topic detection and tracking pilot study: Final report. In Proc. of Broadcast News Transcription and Understanding Workshop , pages 194-218, Lansdowne, VA, 1998. NIST.

[3]

Michael Berry, Murray Browne, Amy Langville, Paul Pauca, and Robert Plemmons. Algorithms and applications for approximate nonnegative matrix factorization. In Submitted to Computational Statistics and Data Analysis, January 2006.

[4]

Scott C. Deerwester, Susan T. Dumais, Thomas K. Landauer, George W. Furnas, and Richard A. Harshman. Indexing by latent semantic analysis. Journal of the American Society of Information Science , 41(6):391-407, 1990.

[5]

Pedro Domingos and Geoff Hulten. Mining high-speed data streams. In Proc. of KDD'00, pages 71-80, New York, NY, USA, 2000. ACM Press.

Digital Library

[6]

David Donoho and Victoria Stodden. When does non-negative matrix factorization give a correct decomposition into parts? In Proc. of NIPS'04. MIT Press, Cambridge, MA, 2004.

[7]

Philip L.H. Yu Edmond H.C. Wu. Independent component analysis for clustering multivariate time series data. Lecture Notes in Computer Science, 3584:474-482, Aug 2005.

Digital Library

[8]

David Guillamet, Jordi Vitrià, and Bernt Schiele. Introducing a weighted non-negative matrix factorization for image classification. Pattern Recognition Letters, 24(14):2447-2454, 2003.

Digital Library

[9]

Thomas Hofmann. Probabilistic latent semantic analysis. In Proc. of UAI'99, Stockholm, 1999.

Digital Library

[10]

Patrik O. Hoyer. Non-negative matrix factorization with sparseness constraints. J. Mach. Learn. Res., 5:1457-1469, 2004.

Digital Library

[11]

R. Plemmons J. Piper, P. Pauca and M. Giffin. Object characterization from spectral data using nonnegative matrix factorization and information theory. In AMOS Technical Conference, Maui, HI, September 2004.

[12]

Daniel D. Lee and H. S. Seung. Learning the parts of objects by non-negative matrix factorization. Nature, 401:788-791, 1999.

[13]

Daniel D. Lee and H. Sebastian Seung. Algorithms for non-negative matrix factorization. In Proc. of NIPS, pages 556-562, 2000.

[14]

S. Li, X. Hou, and H. Zhang. Learning spatially localized, parts-based representation. In Proc. of IEEE CVPR'01.

[15]

Qiaozhu Mei and ChengXiang Zhai. Discovering evolutionary theme patterns from text: an exploration of temporal text mining. In Proc. of KDD '05, pages 198-207, New York, NY, USA, 2005. ACM Press.

Digital Library

[16]

M. Plumbley. Conditions for non-negative independent component analysis. IEEE Signal Processing Letters, 9(6):177-180, 2002.

[17]

Haixun Wang, Wei Fan, Philip S. Yu, and Jiawei Han. Mining concept-drifting data streams using ensemble classifiers. In Proc. of KDD '03, pages 226-235, New York, NY, USA, 2003. ACM Press.

Digital Library

[18]

Stefan Wild, James Curry, and Anne Dougherty. Improving non-negative matrix factorizations through structured initialization. Pattern Recognition, 37(11):2217-2232, 2004.

Digital Library

[19]

Wei Xu and Yihong Gong. Document clustering by concept factorization. In Proc. of SIGIR '04, pages 202-209, New York, NY, USA, 2004. ACM Press.

Digital Library

Cited By

Gong YLi ZZhang JLiu WZheng YKirsch CCuzzocrea AAllan JPaton NSrivastava DAgrawal RBroder AZaki MCandan SLabrinidis ASchuster AWang H(2018)Network-wide Crowd Flow Prediction of Sydney Trains via Customized Online Non-negative Matrix FactorizationProceedings of the 27th ACM International Conference on Information and Knowledge Management10.1145/3269206.3271757(1243-1252)Online publication date: 17-Oct-2018
https://dl.acm.org/doi/10.1145/3269206.3271757
Tu DChen LLv MShi HChen G(2018)Hierarchical online NMF for detecting and tracking topic hierarchies in a text streamPattern Recognition10.1016/j.patcog.2017.11.00276:C(203-214)Online publication date: 1-Apr-2018
https://dl.acm.org/doi/10.1016/j.patcog.2017.11.002
Zhu FHoneine P(2017)Online kernel nonnegative matrix factorizationSignal Processing10.1016/j.sigpro.2016.08.011131:C(143-153)Online publication date: 1-Feb-2017
https://dl.acm.org/doi/10.1016/j.sigpro.2016.08.011
Show More Cited By

Recommendations

Heuristics for exact nonnegative matrix factorization

The exact nonnegative matrix factorization (exact NMF) problem is the following: given an m-by-n nonnegative matrix X and a factorization rank r, find, if possible, an m-by-r nonnegative matrix W and an r-by-n nonnegative matrix H such that $$X = WH$$X=...
Symmetric nonnegative matrix factorization: A systematic review
Abstract
In recent years, symmetric non-negative matrix factorization (SNMF), a variant of non-negative matrix factorization (NMF), has emerged as a promising tool for data analysis. This paper mainly focuses on the theoretical idea, the basic ...
Highlights
- This paper reviews symmetric non-negative matrix factorization (SNMF).
- We ...
Quadratic nonnegative matrix factorization

In Nonnegative Matrix Factorization (NMF), a nonnegative matrix is approximated by a product of lower-rank factorizing matrices. Most NMF methods assume that each factorizing matrix appears only once in the approximation, thus the approximation is ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

IJCAI'07: Proceedings of the 20th international joint conference on Artifical intelligence

January 2007

2953 pages

Editors:
Rajeev Sangal
International Institute of Information Technology, Hyderabad
,
Harish Mehta
Onward Technologies Limited
,
R. K. Bagga
International Institute of Information Technology, Hyderabad

Sponsors

The International Joint Conferences on Artificial Intelligence, Inc.

Publisher

Morgan Kaufmann Publishers Inc.

San Francisco, CA, United States

Publication History

Published: 06 January 2007

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

14
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Gong YLi ZZhang JLiu WZheng YKirsch CCuzzocrea AAllan JPaton NSrivastava DAgrawal RBroder AZaki MCandan SLabrinidis ASchuster AWang H(2018)Network-wide Crowd Flow Prediction of Sydney Trains via Customized Online Non-negative Matrix FactorizationProceedings of the 27th ACM International Conference on Information and Knowledge Management10.1145/3269206.3271757(1243-1252)Online publication date: 17-Oct-2018
https://dl.acm.org/doi/10.1145/3269206.3271757
Tu DChen LLv MShi HChen G(2018)Hierarchical online NMF for detecting and tracking topic hierarchies in a text streamPattern Recognition10.1016/j.patcog.2017.11.00276:C(203-214)Online publication date: 1-Apr-2018
https://dl.acm.org/doi/10.1016/j.patcog.2017.11.002
Zhu FHoneine P(2017)Online kernel nonnegative matrix factorizationSignal Processing10.1016/j.sigpro.2016.08.011131:C(143-153)Online publication date: 1-Feb-2017
https://dl.acm.org/doi/10.1016/j.sigpro.2016.08.011
Liu CHoi SZhao PSun JLim EMukhopadhyay SZhai CBertino ECrestani FMostafa JTang JSi LZhou XChang YLi YSondhi P(2016)Online Adaptive Passive-Aggressive Methods for Non-Negative Matrix Factorization and Its ApplicationsProceedings of the 25th ACM International on Conference on Information and Knowledge Management10.1145/2983323.2983786(1161-1170)Online publication date: 24-Oct-2016
https://dl.acm.org/doi/10.1145/2983323.2983786
Hayashi KMaehara TToyoda MKawarabayashi KCao LZhang CJoachims TWebb GMargineantu DWilliams G(2015)Real-Time Top-R Topic Detection on Twitter with Topic Hijack FilteringProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining10.1145/2783258.2783402(417-426)Online publication date: 10-Aug-2015
https://dl.acm.org/doi/10.1145/2783258.2783402
Zhu LGalstyan ACheng JLerman KDyreson CLi FÖzsu M(2014)Tripartite graph clustering for dynamic sentiment analysis on social mediaProceedings of the 2014 ACM SIGMOD International Conference on Management of Data10.1145/2588555.2593682(1531-1542)Online publication date: 18-Jun-2014
https://dl.acm.org/doi/10.1145/2588555.2593682
Vaca CMantrach AJaimes ASaerens MChung CBroder AShim KSuel T(2014)A time-based collective factorization for topic discovery and monitoring in newsProceedings of the 23rd international conference on World wide web10.1145/2566486.2568041(527-538)Online publication date: 7-Apr-2014
https://dl.acm.org/doi/10.1145/2566486.2568041
Kim JHe YPark H(2014)Algorithms for nonnegative matrix and tensor factorizationsJournal of Global Optimization10.1007/s10898-013-0035-458:2(285-319)Online publication date: 1-Feb-2014
https://dl.acm.org/doi/10.1007/s10898-013-0035-4
Wang DLu H(2013)On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorizationSignal Processing10.1016/j.sigpro.2012.07.01593:6(1608-1623)Online publication date: 1-Jun-2013
https://dl.acm.org/doi/10.1016/j.sigpro.2012.07.015
Wang FLee NHu JSun JEbadollahi SYang QAgarwal DPei J(2012)Towards heterogeneous temporal clinical event pattern discoveryProceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining10.1145/2339530.2339605(453-461)Online publication date: 12-Aug-2012
https://dl.acm.org/doi/10.1145/2339530.2339605
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents