The goal of the seminar is to study different methods for non-negative matrix factorization, as well as its applications to machine learning, information retrieval and recommender systems. In each session, two different papers will be presented by students. The evaluation of the course will be exclusively based on the presentation of the papers.


 Date        Paper & PresenterResources
Feb 15 2010[Lee and Seung, 1999] Anyela
Learning the Parts of Objects using. Non-negative Matrix Factorization. (NMF). [url
Ralf Nikolaus
[report] [slides]
 [Lee and Seung, 2001] Paola Algorithms for Non-negative Matrix Factorization. [slides]
Feb 22 2010  [Xu, Liu and Gong, 2003] Angel [slides]
 [Koren, Bell and Volinsky, 2009] Andrés  
Mar 1 2010[Ding, He and Simon, 2005] Jorge 
 [Gaussier and Goutte, 2005] José Guillermo [slides]
Mar 8 2010[Zhang, Zhou and Chen, 2006] Raul [slides]
Marzo 15 2010
[Taylan, 2009]  Anyela - Katherine
Abril 5 2010

Abril 12 2010
Abril 17 2010
  [Boutsidis,2008] José Guillermo


[Y. Chen, L. Wang, and M. Dong, 2009] Y. Chen, L. Wang, and M. Dong, "Non-negative matrix factorization for semi-supervised heterogeneous data co-clustering,"IEEE Transactions on Knowledge and Data Engineering, vol. 99, no. 1, 2009. [Online]. Available: http://dx.doi.org/10.1109/TKDE.2009.169

[S. Bucak and B. Gunsel, 2009] S. Bucak and B. Gunsel, "Incremental subspace learning via non-negative matrix factorization," Pattern Recognition, vol. 42, no. 5, pp. 788-797, May 2009. [Online]. Available: http://dx.doi.org/10.1016/j.patcog.2008.09.002

[Ding, He and Simon, 2005] Ding, C., X. He, and H. D. Simon. 2005. On  the equivalence of nonnegative matrix factorization and spectral  clustering. In Proc. SIAM Data Mining Conf, 606–610.

[Ding, Li and Jordan, 2010] Ding, C., T. Li, and M. I. Jordan. 2010. Convex and semi-nonnegative matrix factorizations. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(1):45–55.

[Ding, Li and Peng, 2006] Ding, C., T. Li, and W. Peng. 2006. Nonnegative matrix factorization and probabilistic latent semantic indexing: equivalence, chi-square statistic, and a hybrid method. In AAAI’06: Proceedings of the 21st national conference on Artificial intelligence held in Boston, Massachusetts, 342–347. AAAI Press.
[Gaussier and Goutte, 2005] Gaussier, E., and C. Goutte. 2005. Relation between plsa and nmf and implications. In SIGIR ’05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval held in Salvador, Brazil, 601–602. ACM.

[Koren, Bell and Volinsky, 2009] Koren, Y., R. Bell, and C. Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42(8):30–37.
[Lee and Seung, 1999] Lee, D. D., and H. S. Seung. 1999. Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791
[Lee and Seung, 2001] Lee, D. D., and H. S. Seung. 2001. Algorithms for non-negative matrix factorization. Advances in neural information processing systems:556–562

[Takács et al., 2009] Takács, G., I. Pilászy, B. Németh, and D. Tikk. 2009. Scalable collaborative filtering approaches for large recommender systems. J. Mach. Learn. Res. 10:623–656
[Xu, Liu and Gong, 2003] Xu, W., X. Liu, and Y. Gong. 2003. Document clustering based on non-negative matrix factorization. In SIGIR ’03: Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, 267–273. ACM.

[Zass and Shashua, 2005] Zass, R., and A. Shashua. 2005. A unifying approach to hard and probabilistic clustering. In ICCV ’05: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, 294–301. IEEE Computer Society
[Zhang, Zhou and Chen, 2006] Zhang, D., Z.-H. Zhou, and S. Chen. 2006. Non-negative matrix factorization on kernels. 404–412.

[Taylan, 2009] Ali Taylan Cemgil, Bayesian Inference for Nonnegative Matrix Factorisation Models, Computational Intelligence and Neuroscience, vol. 2009, Article ID 785152, 17 pages, 2009.

[Boutsidis, 2008] C. Boutsidis and E. Gallopoulos, SVD based initialization: A head start for nonnegative matrix factorization, Pattern Recognition. Volume 41, Issue 4, April 2008, Pages 1350-1362.


Matlab NMF Implementation
Technical University of Denmark. NMF:DTUToolbox http://isp.imm.dtu.dk/toolbox/nmf/
Paola Katherine Rozo Bernal,
Apr 19, 2010, 2:35 PM
Angel Cruz,
Mar 2, 2010, 2:20 PM
Raul Ernesto Torres Carvajal,
Mar 8, 2010, 8:05 AM
Jose G Moreno,
Apr 19, 2010, 1:55 PM
Jose G Moreno,
Mar 8, 2010, 11:02 AM