
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
Pauli Miettinen, Taneli Mielikäinen, Aristides Gionis, Gautam Das, Heikki Mannila, "The Discrete Basis Problem," IEEE Transactions on Knowledge and Data Engineering, vol. 20, no. 10, pp. 13481362, October, 2008.  
BibTex  x  
@article{ 10.1109/TKDE.2008.53, author = {Pauli Miettinen and Taneli Mielikäinen and Aristides Gionis and Gautam Das and Heikki Mannila}, title = {The Discrete Basis Problem}, journal ={IEEE Transactions on Knowledge and Data Engineering}, volume = {20}, number = {10}, issn = {10414347}, year = {2008}, pages = {13481362}, doi = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2008.53}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Knowledge and Data Engineering TI  The Discrete Basis Problem IS  10 SN  10414347 SP1348 EP1362 EPD  13481362 A1  Pauli Miettinen, A1  Taneli Mielikäinen, A1  Aristides Gionis, A1  Gautam Das, A1  Heikki Mannila, PY  2008 KW  Mining methods and algorithms KW  Clustering KW  classification KW  and association rules KW  Text mining VL  20 JA  IEEE Transactions on Knowledge and Data Engineering ER   
[1] P. Miettinen, T. Mielikäinen, A. Gionis, G. Das, and H. Mannila, “The Discrete Basis Problem,” Proc. 10th European Conf. Principles and Practice of Knowledge Discovery in Databases (PKDD '06), pp.335346, 2006.
[2] G. Golub and C. van Loan, Matrix Computations. Johns Hopkins Univ. Press, 1996.
[3] D. Lee and H. Seung, “Learning the Parts of Objects by NonNegative Matrix Factorization,” Nature, vol. 401, pp. 788791, 1999.
[4] D. Blei, A. Ng, and M. Jordan, “Latent Dirichlet Allocation,” J.Machine Learning Research, vol. 3, pp. 9931022, 2003.
[5] W. Buntine, “Variational Extensions to EM and Multinomial PCA,” Proc. 13th European Conf. Machine Learning (ECML '02), pp.2334, Aug. 2002.
[6] P. Paatero and U. Tapper, “Positive Matrix Factorization: A NonNegative Factor Model with Optimal Utilization of Error Estimates of Data Values,” Environmetrics, vol. 5, pp. 111126, 1994.
[7] J.E. Cohen and U.G. Rothblum, “Nonnegative Ranks, Decompositions, and Factorizations of Nonnegative Matrices,” Linear Algebra and Its Applications, vol. 190, pp. 149168, 1993.
[8] M.W. Berry, M. Browne, A.N. Langville, V.P. Pauca, and R.J. Plemmons, “Algorithms and Applications for Approximate Nonnegative Matrix Factorization,” Computational Statistics and Data Analysis, vol. 52, pp. 155173, 2007.
[9] T. Hofmann, “Probabilistic Latent Semantic Indexing,” Proc. 22nd Ann. Int'l ACM Conf. Research and Development in Information Retrieval (SIGIR '99), pp. 5057, Aug. 1999.
[10] W. Buntine and A. Jakulin, “Discrete Component Analysis,” Proc. Subspace, Latent Structure and Feature Selection, Statistical and Optimization, Perspectives Workshop (SLSFS '05), pp. 133, 2006.
[11] E. Bingham, A. Kabán, and M. Fortelius, “The Aspect Bernoulli Model: Multiple Causes of Presences and Absences,” to be published in Pattern Analysis and Applications, 2008.
[12] J. Seppänen, E. Bingham, and H. Mannila, “A Simple Algorithm for Topic Identification in 01 Data,” Proc. Seventh European Conf. Principles and Practice of Knowledge Discovery in Databases (PKDD '03), pp. 423434, 2003.
[13] A.I. Schein, L.K. Saul, and L.H. Ungar, “A Generalized Linear Model for Principal Component Analysis of Binary Data,” Proc. Ninth Int'l Workshop Artificial Intelligence and Statistics (AI & Statistics), 2003.
[14] D.P. O'Leary and S. Peleg, “Digital Image Compression by Outer Product Expansion,” IEEE Trans. Comm., vol. 31, no. 3, pp. 441444, 1983.
[15] T.G. Kolda and D.P. O'Leary, “A Semidiscrete Matrix Decomposition for Latent Semantic Indexing in Information Retrieval,” ACM Trans. Information Systems, vol. 16, no. 4, pp. 322346, 1998.
[16] M.W. Berry, S.A. Pulatova, and G.W. Stewart, “Algorithm 844: Computing Sparce ReducedRank Approximations to Sparce Matrices,” ACM Trans. Math. Software, vol. 31, no. 2, pp. 252269, 2005.
[17] P. Drineas, R. Kannan, and M.W. Mahoney, “Fast Monte Carlo Algorithms for Matrices III: Computing a Compressed Approximate Matrix Decomposition,” SIAM J. Computing, vol. 36, no. 1, pp. 184206, 2006.
[18] P. Drineas, M.W. Mahoney, and S. Muthukrishnan, RelativeError CUR Matrix Decompositions, arXiv:0708.3696v1 [cs.DS], http://arxiv.org/abs0708.3696, Aug. 2007.
[19] M. Koyutürk, A. Grama, and N. Ramakrsihnan, “Compression, Clustering, and Pattern Discovery in VeryHighDimensional DiscreteAttribute Data Sets,” IEEE Trans. Knowledge Data Eng., vol. 17, pp. 447461, 2005.
[20] A. Gionis, H. Mannila, and J.K. Seppänen, “Geometric and Combinatorial Tiles in 01 Data,” Proc. Eighth European Conf. Principles and Practice of Knowledge Discovery in Databases (PKDD '04), pp. 173184, 2004.
[21] F. Geerts, B. Goethals, and T. Mielikäinen, “Tiling Databases,” Proc. Seventh Int'l Conf. Discovery Science (DS '04), pp.278289, 2004.
[22] J. Besson, R. Pensa, C. Robardet, and J.F. Boulicaut, “ConstraintBased Mining of FaultTolerant Patterns from Boolean Data,” Proc. Fourth Int'l Workshop Knowledge Discovery in Inductive Databases (KDID '06), pp. 5571, 2006.
[23] N. Mishra, D. Ron, and R. Swaminathan, “A New Conceptual Clustering Framework,” Machine Learning, vol. 56, pp. 115151, 2004.
[24] R.K. Brayton, G.D. Hachtel, and A.L. SangiovanniVincentelli, “Multilevel Logic Synthesis,” Proc. IEEE, vol. 78, no. 2, pp. 264300, 1990.
[25] J.A. Hartigan, “Direct Clustering of a Data Matrix,” J. Am. Statistical Assoc., vol. 67, no. 337, pp. 123129, 1972.
[26] A. Banerjee, I.S. Dhillon, J. Ghosh, S. Merugu, and D.S. Modha, “A Generalized Maximum Entropy Approach to Bregman CoClustering and Matrix Approximations,” Proc. 10th ACM SIGKDD Int'l Conf. Knowledge Discovery and Data Mining (KDD '04), pp. 509514, 2004.
[27] S. Madeira and A. Oliveira, “Biclustering Algorithms for Biological Data Analysis: A Survey,” IEEE/ACM Trans. Computational Biology and Bioinformatics, vol. 1, no. 1, pp. 2445, Jan.Mar. 2004.
[28] C. Robardet and F. Feschet, “Efficient Local Search in Conceptual Clustering,” Proc. Fourth Int'l Conf. Discovery Science (DS '01), pp.323335, 2001.
[29] J. Vaidya, V. Atluri, and Q. Guo, “The Role Mining Problem: Finding a Minimal Descriptive Set of Roles,” Proc. ACM Symp. Access Control Models and Technologies (SACMAT '07), pp. 175184, 2007.
[30] H. Lu, J. Vaidya, and V. Atluri, “Optimal Boolean Matrix Decomposition: Application to Role Engineering,” Proc. IEEE Int'l Conf. Data Eng. (ICDE '08), pp. 297306, Apr. 2008.
[31] S.D. Monson, N.J. Pullman, and R. Rees, “A Survey of Clique and Biclique Coverings and Factorizations of (0, 1)Matrices,” Bull. Inst. Combinatorics and Its Applications, vol. 14, pp. 1786, 1995.
[32] D.A. Gregory and N.J. Pullman, “Semiring Rank: Boolean Rank and Nonnegative Rank Factorizations,” J. Combinatorics, Information and System Sciences, vol. 8, no. 3, pp. 223233, 1983.
[33] M.R. Garey and D.S. Johnson, Computers and Intractability: A Guide to the Theory of NPCompleteness. W.H. Freeman, 1979.
[34] H.U. Simon, “On Approximate Solutions for Combinatorial Optimization Problems,” SIAM J. Discrete Math., vol. 3, no. 2, pp. 294310, 1990.
[35] R.G. Downey and M.R. Fellows, “Parameterized Complexity,” Monographs in Computer Science. SpringerVerlag, 1999.
[36] J. Flum and M. Grohe, Parameterized Complexity Theory. Springer, 2006.
[37] N. Megiddo and K. Supowit, “On the Complexity of Some Common Geometric Location Problems,” SIAM J. Computing, vol. 13, no. 1, pp. 182196, 1984.
[38] V. Arya, N. Garg, R. Kjandekar, A. Meyerson, K. Munagala, and V. Pandit, “Local Search Heuristics for kMedian and Facility Location Problems,” SIAM J. Computing, vol. 33, no. 3, pp. 544562, 2004.
[39] R. Agrawal, T. Imielinski, and A. Swami, “Mining Association Rules between Sets of Items in Large Databases,” Proc. ACM SIGMOD '93, pp. 207216, May 1993.
[40] K. Lang, “Newsweeder: Learning to Filter Netnews,” Proc. 12th Int'l Conf. Machine Learning (ICML '95), pp. 331339, 1995.
[41] D. Newman, S. Hettich, C. Blake, and C. Merz, “UCI Repository of Machine Learning Databases,” http://www.ics.uci.edu/~mlearnMLRepository.html , 1998.
[42] M. Fortelius, Neogene of the Old World Database of Fossil Mammals (NOW '05), http://www.helsinki.fi/sciencenow/, 2005.
[43] A. Pajala and A. Jakulin, “Plenary Votes in the Finnish Parliament during 19912005,” Tampere: Finnish Social Science Data Archive, http://www.fsd.uta.fienglish/, 2006.
[44] D. Lee and H. Seung, “Algorithms for NonNegative Matrix Factorization,” Advances in Neural Information Processing Systems, vol. 13, pp. 556562, 2001.