Orthogonal nonnegative matrix t-factorizations for clustering TeX Export

@inproceedings{citeulike:1168276, abstract = {Currently, most research on nonnegative matrix factorization (NMF)focus on 2-factor \$X=FG^T\$ factorization. We provide a systematicanalysis of 3-factor \$X=FSG^T\$ NMF. While it unconstrained 3-factor NMF is equivalent to it unconstrained 2-factor NMF, itconstrained 3-factor NMF brings new features to it constrained 2-factor NMF. We study the orthogonality constraint because it leadsto rigorous clustering interpretation. We provide new rules for updating \$F,S, G\$ and prove the convergenceof these algorithms. Experiments on 5 datasets and a real world casestudy are performed to show the capability of bi-orthogonal 3-factorNMF on simultaneously clustering rows and columns of the input datamatrix. We provide a new approach of evaluating the quality ofclustering on words using class aggregate distribution andmulti-peak distribution. We also provide an overview of various NMF extensions andexamine their relationships.}, address = {New York, NY, USA}, author = {Ding, Chris and Li, Tao and Peng, Wei and Park, Haesun}, booktitle = {KDD '06: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {1168276}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1150402.1150420}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1150402.1150420}, doi = {10.1145/1150402.1150420}, isbn = {1-59593-339-5}, keywords = {clustering, matrix}, location = {Philadelphia, PA, USA}, pages = {126--135}, posted-at = {2007-03-17 06:00:53}, priority = {2}, publisher = {ACM}, title = {Orthogonal nonnegative matrix t-factorizations for clustering}, url = {http://dx.doi.org/10.1145/1150402.1150420}, year = {2006} }

TY - CONF ID - citeulike:1168276 L3 - citeulike-article-id:1168276 N2 - Currently, most research on nonnegative matrix factorization (NMF)focus on 2-factor $X=FG^T$ factorization. We provide a systematicanalysis of 3-factor $X=FSG^T$ NMF. While it unconstrained 3-factor NMF is equivalent to it unconstrained 2-factor NMF, itconstrained 3-factor NMF brings new features to it constrained 2-factor NMF. We study the orthogonality constraint because it leadsto rigorous clustering interpretation. We provide new rules for updating $F,S, G$ and prove the convergenceof these algorithms. Experiments on 5 datasets and a real world casestudy are performed to show the capability of bi-orthogonal 3-factorNMF on simultaneously clustering rows and columns of the input datamatrix. We provide a new approach of evaluating the quality ofclustering on words using class aggregate distribution andmulti-peak distribution. We also provide an overview of various NMF extensions andexamine their relationships. CY - Philadelphia, PA, USA SN - 1-59593-339-5 AD - New York, NY, USA EP - 135 TI - Orthogonal nonnegative matrix t-factorizations for clustering PB - ACM T2 - KDD '06: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining SP - 126 KW - clustering KW - matrix AU - Ding, Chris AU - Li, Tao AU - Peng, Wei AU - Park, Haesun PY - 2006/// UR - http://dx.doi.org/10.1145/1150402.1150420 ER -