Initialization enhancer for non-negative matrix factorization

Authors:
Zhonglong Zheng;Jie Yang;Yitan Zhu
Affiliations:
Institute of Information Science and Engineering, P.O. box 143, Zhejiang Normal University, Jinhua 321004, Zhejiang, People's Republic of China and Institute of Image Processing and Pattern Recogn ...;Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200030, People's Republic of China;Alexandria Research Institute, Virginia Polytechnic Institute and State University, 206 N. Washington Street, Alexandria, VA 22314, USA
Venue:
Engineering Applications of Artificial Intelligence
Year:
2007

Citing 9
Cited 6

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Image Representation Using 2D Gabor Wavelets

IEEE Transactions on Pattern Analysis and Machine Intelligence
Concept decompositions for large sparse text data using clustering

Machine Learning
Extracting Text from WWW Images

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Introducing a weighted non-negative matrix factorization for image classification

Pattern Recognition Letters
Application of non-Negative and Local non Negative Matrix Factorization to Facial Expression Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Eigenfaces for recognition

Journal of Cognitive Neuroscience
A "nonnegative PCA" algorithm for independent component analysis

IEEE Transactions on Neural Networks
Learning in linear neural networks: a survey

IEEE Transactions on Neural Networks

Fast communication: Unsupervised data reduction

Signal Processing
Adaptive harmonic spectral decomposition for multiple pitch estimation

IEEE Transactions on Audio, Speech, and Language Processing
Normalized dimensionality reduction using nonnegative matrix factorization

Neurocomputing
Subtractive initialization of nonnegative matrix factorizations for document clustering

WILF'11 Proceedings of the 9th international conference on Fuzzy logic and applications
Subtractive clustering for seeding non-negative matrix factorizations

Information Sciences: an International Journal
Beyond cross-domain learning: Multiple-domain nonnegative matrix factorization

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Non-negative matrix factorization (NMF), proposed recently by Lee and Seung, has been applied to many areas such as dimensionality reduction, image classification image compression, and so on. Based on traditional NMF, researchers have put forward several new algorithms to improve its performance. However, particular emphasis has to be placed on the initialization of NMF because of its local convergence, although it is usually ignored in many documents. In this paper, we explore three initialization methods based on principal component analysis (PCA), fuzzy clustering and Gabor wavelets either for the consideration of computational complexity or the preservation of structure. In addition, the three methods develop an efficient way of selecting the rank of the NMF in low-dimensional space.