Sparse nonnegative matrix factorization with ?sup>0-constraints

详细信息    查看全文

• 作者：Robert Peharz ; ^{robert.peharz@tugraz.at}  ; [Author Vitae] ; Franz Pernkopf  ; [Author Vitae]
• 关键词：NMF ; Sparse coding ; Nonnegative least squares
• 刊名：Neurocomputing
• 出版年：2012
• 出版时间：15 March, 2012
• 年：2012
• 卷：80
• 期：Complete
• 页码：38-46
• 全文大小：541 K

文摘

Although nonnegative matrix factorization (NMF) favors a sparse and part-based representation of nonnegative data, there is no guarantee for this behavior. Several authors proposed NMF methods which enforce sparseness by constraining or penalizing the of the factor matrices. On the other hand, little work has been done using a more natural sparseness measure, the . In this paper, we propose a framework for approximate NMF which constrains the of the basis matrix, or the coefficient matrix, respectively. For this purpose, techniques for unconstrained NMF can be easily incorporated, such as multiplicative update rules, or the alternating nonnegative least-squares scheme. In experiments we demonstrate the benefits of our methods, which compare to, or outperform existing approaches.