Diverse Non-Negative Matrix Factorization for Multiview Data Representation

Authors: Wang, J., Tian, F., Yu, H.C., liu, C.H.A.N.G.H.O.N.G., Zhan, K. and Wang, X.

http://eprints.bournemouth.ac.uk/29958/

Journal: IEEE Transactions on Cybernetics

Publisher: IEEE Advancing Technology for Humanity

ISSN: 2168-2267

This data was imported from Scopus:

Authors: Wang, J., Tian, F., Yu, H., Liu, C.H., Zhan, K. and Wang, X.

http://eprints.bournemouth.ac.uk/29958/

Journal: IEEE Transactions on Cybernetics

Volume: 48

Issue: 9

Pages: 2620-2632

ISSN: 2168-2267

DOI: 10.1109/TCYB.2017.2747400

© 2013 IEEE. Non-negative matrix factorization (NMF), a method for finding parts-based representation of non-negative data, has shown remarkable competitiveness in data analysis. Given that real-world datasets are often comprised of multiple features or views which describe data from various perspectives, it is important to exploit diversity from multiple views for comprehensive and accurate data representations. Moreover, real-world datasets often come with high-dimensional features, which demands the efficiency of low-dimensional representation learning approaches. To address these needs, we propose a diverse NMF (DiNMF) approach. It enhances the diversity, reduces the redundancy among multiview representations with a novel defined diversity term and enables the learning process in linear execution time. We further propose a locality preserved DiNMF (LP-DiNMF) for more accurate learning, which ensures diversity from multiple views while preserving the local geometry structure of data in each view. Efficient iterative updating algorithms are derived for both DiNMF and LP-DiNMF, along with proofs of convergence. Experiments on synthetic and real-world datasets have demonstrated the efficiency and accuracy of the proposed methods against the state-of-the-art approaches, proving the advantages of incorporating the proposed diversity term into NMF.

The data on this page was last updated at 04:52 on November 15, 2018.