Convex and semi-nonnegative matrix factorizations

We present several new variations on the theme of nonnegative matrix factorization (NMF). Considering factorizations of the form X=FG(T), we focus on algorithms in which G is restricted to containing nonnegative entries, but allowing the data matrix X to have mixed signs, thus extending the applicab...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 32(2010), 1 vom: 20. Jan., Seite 45-55
1. Verfasser: Ding, Chris (VerfasserIn)
Weitere Verfasser: Li, Tao, Jordan, Michael I
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2010
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM192953605
003 DE-627
005 20231223193909.0
007 cr uuu---uuuuu
008 231223s2010 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2008.277  |2 doi 
028 5 2 |a pubmed24n0643.xml 
035 |a (DE-627)NLM192953605 
035 |a (NLM)19926898 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ding, Chris  |e verfasserin  |4 aut 
245 1 0 |a Convex and semi-nonnegative matrix factorizations 
264 1 |c 2010 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 25.01.2010 
500 |a Date Revised 20.11.2009 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We present several new variations on the theme of nonnegative matrix factorization (NMF). Considering factorizations of the form X=FG(T), we focus on algorithms in which G is restricted to containing nonnegative entries, but allowing the data matrix X to have mixed signs, thus extending the applicable range of NMF methods. We also consider algorithms in which the basis vectors of F are constrained to be convex combinations of the data points. This is used for a kernel extension of NMF. We provide algorithms for computing these new factorizations and we provide supporting theoretical analysis. We also analyze the relationships between our algorithms and clustering algorithms, and consider the implications for sparseness of solutions. Finally, we present experimental results that explore the properties of these new methods 
650 4 |a Journal Article 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Li, Tao  |e verfasserin  |4 aut 
700 1 |a Jordan, Michael I  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 32(2010), 1 vom: 20. Jan., Seite 45-55  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:32  |g year:2010  |g number:1  |g day:20  |g month:01  |g pages:45-55 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2008.277  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 32  |j 2010  |e 1  |b 20  |c 01  |h 45-55