Abstract
In order to reduce redundant information in data classification and improve classification accuracy, a novel approach based on nonnegative matrix factorization and harmonic functions (NMF–HF) is proposed for semi-supervised learning. Firstly, we extract the feature data from the original data by nonnegative matrix factorization (NMF) and then classify the original data by harmonic functions (HF) on the basis of the feature data. Empirical results show that NMF–HF can effectively reduce the redundant information and improve the classification accuracy compared with some state-of-the-art approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, X., Ghahramani, Z., & Lafferty, J. (2003). Semi-supervised learning using gaussian fields and harmonic functions. In Proceedings of the 20th International Conference on Machine Learning (Vol. 20, Issue 2, p. 912). Washington, DC: AAAI Press.
Belkin, M., & Niyogi, P. (2002). Using manifold structure for partially labelled classification. Advances in Neural Information Processing Systems, 15, 929–936.
Blum, A., & Chawla, S. (2001). Learning from labeled and unlabeled data using graph mincuts. In Proceedings of the 18th International Conference on Machine Learning (pp. 19–26). Williams College: Morgan Kaufmann.
Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects with non-negative matrix factorization. Nature, 401(6755), 788–791.
Student, M., & Eswar, K. (2012). Graph regularized non-negative matrix factorization for data representation. International Journal of Computer Application, 3(2), 171–191.
Cichocki, A., & Amari, S. (2002). Adaptive blind signal and image processing. In Learning algorithms and applications (pp. 88–93). New York, NY: John Wiley Press.
Ding, C., Li, T., & Jordan, M. (2008). Nonnegative matrix factorization for combinatorial optimization: Spectral clustering, graph matching, and clique finding. In ICDM (pp. 183–192). Pisa, Italy: IEEE Computer Society.
He, Z., Xie, S., Zdunek, R., Zhou, G., & Cichocki, A. (2011). Symmetric nonnegative matrix factorization: Algorithms and applications to probabilistic clustering. IEEE Transactions on Neural Networks, 22(12), 2117–2131.
Berry, M. W., Browne, M., Langville, A. N., Pauca, V. P., & Plemmons, R. J. (2007). Algorithms and applications for approximate nonnegative matrix factorization. Computational Statistics and Data Analysis, 52(1), 155–173.
Sajda, P., Du, S., & Parra, L. C. (2003). Recovery of constituent spectra using nonnegative matrix factorization. Optical Science and Technology, SPIE’s 48th Annual Meeting. Proceedings of SPIE, San Diego. pp. 321–331.
Lee, D. D., & Seung, H. S. (2001). Algorithms for nonnegative matrix factorization. Advances in Neural Information Processing Systems, 13, 556–562.
Acknowledgments
We gratefully acknowledge the supports from National Natural Science Foundation of China, under Grant No 61005003.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, L., Zhao, Z., Hou, C., Wu, Y. (2014). Semi-supervised Learning Using Nonnegative Matrix Factorization and Harmonic Functions. In: Wong, W.E., Zhu, T. (eds) Computer Engineering and Networking. Lecture Notes in Electrical Engineering, vol 277. Springer, Cham. https://doi.org/10.1007/978-3-319-01766-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-01766-2_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-01765-5
Online ISBN: 978-3-319-01766-2
eBook Packages: EngineeringEngineering (R0)