Abstract
We propose an enhanced label prediction method termed Transductive Classification Robust Linear Neighborhood Propagation (R-LNP). To encode the neighborhood reconstruction error more accurately, we apply the L2,1-norm that is proved to be very robust to noise for characterizing the manifold smoothing term. Since L2,1-norm can also enforce the neighborhood reconstruction error to be sparse in rows, i.e., entries of some rows are zeros. In addition, to enhance robustness in the process of modeling the difference between the initial labels and predicted ones, we also regularize the weighted L2,1-norm on the label fitting term, so the resulted measures would be more accurate. Compared with several transductive label propagation models, our proposed algorithm obtains state-of-the-art performance over extensive representation and classification experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, F., Zhang, C.: Label propagation through linear neighborhoods. IEEE Trans. Knowl. Data Eng. 20(1), 55–67 (2008)
Wang, Y., Chen, S., Zhou, Z.H.: New semi-supervised classification method based on modified cluster assumption. IEEE Trans. Neural Netw. Learn. Syst. 23(5), 689–702 (2012)
Zhang, F., Yang, J., Qian, J.: Nuclear norm-based 2-DPCA for extracting features from images. IEEE Trans. Neural Netw. Learn. Syst. 26(10), 2247–2260 (2015)
Yang, Y., Shen, H.T.: L2,1-norm regularized discriminative feature selection for unsupervised learning. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, vol. 2, pp. 1589–1594 (2011)
Data, C., Mining, D.: Concepts and techniques. San Franc. 29(1), 1–18 (2010)
Zhang, F., Zhang, J.S.: Label propagation through sparse neighborhood and its applications. Neurocomputing 97, 267–277 (2012)
Wang, J.: Locally Linear Embedding. Springer, Heidelberg (2012)
Zhang, C., Wang, S., Li, D.: Prior class dissimilarity based linear neighborhood propagation. Knowl. Based Syst. 83, 58–65 (2015)
Nie, F., Xiang, S., Liu, Y.: A general graph-based semi-supervised learning with novel class discovery. Neural Comput. Appl. 19(4), 549–555 (2010)
Zhang, Z., Zhang, L., Zhao, M.B., Jiang, W.M., Liang, Y.C., Li, F.Z.: Semi-supervised image classification by nonnegative sparse neighborhood propagation. In: Proceedings of the ACM International Conference on Multimedia Retrieval, Shanghai, pp. 139–146 (2015)
Tang, H., Fang, T., Shi, P.F.: Laplacian linear discriminant analysis. Pattern Recognit. 39(1), 136–139 (2006)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Scholkopf, B.: Learning with local and global consistency. Adv. Neural Inf. Proces. Syst. 17(4), 321–328 (2004)
Zhu, X., Ghahramani, Z., Lafferty, J.: Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of 20th International Conference on Machine Learning, pp. 912–919 (2003)
Hou, C.P., Nie, F.P., Li, X.L., Yi, D.Y., Wu, Y.: Joint embedding learning and sparse regression: a framework for unsupervised feature selection. IEEE Trans. Cybern. 44(6), 793–804 (2014)
Nie, F., Huang, H., Cai, X., Ding, C.: Efficient and robust feature selection via joint L2,1-norms minimization. In: Advances in Neural Information Processing Systems, pp. 1813–121 (2010)
Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library (COIL-20). Technical report CUCS-005-96 (1996)
Yang, S.Z., Hou, C.P., Nie, F.P., Wu, Y.: Unsupervised maximum margin feature selection via L2,1-norm minimization. Neural Comput. Appl. 21(7), 1791–1799 (2012)
Zhang, Z., Jiang, W., Li, F., Zhang, L., Zhao, M., Jia, L.: Projective Label Propagation by Label Embedding. In: Azzopardi, G., Petkov, N. (eds.) CAIP 2015. LNCS, vol. 9257, pp. 470–481. Springer, Heidelberg (2015). doi:10.1007/978-3-319-23117-4_41
Zhao, M.B., Chow, T.W.S., Zhang, Z., Li, B.: Automatic image annotation via compact graph based semi-supervised learning. Know. Based Syst. 76, 148–165 (2015)
Liang, Y.C., Zhang, Z., Jiang, W.M., Zhao, M.B., Li, F.Z.: Bilinear embedding label propagation: towards scalable prediction of image labels. IEEE Signal Process. Lett. 22(12), 2411–2415 (2015)
Acknowledgments
This work is partially supported by the National Natural Science Foundation of China (61402310, 61672365, 61672364 and 61373093), Major Program of Natural Science Foundation of Jiangsu Higher Education Institutions of China (15KJA520002), Special Funding of China Postdoctoral Science Foundation (2016T90494), Postdoctoral Science Foundation of China (2015M580462) and Postdoctoral Science Foundation of Jiangsu Province of China (1501091B), Natural Science Foundation of Jiangsu Province of China (BK20140008, BK20141195), and Graduate Student Innovation Project of Jiangsu Province of China (SJZZ15_0154, SJZZ16_0236).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Jia, L., Zhang, Z., Jiang, W. (2016). Transductive Classification by Robust Linear Neighborhood Propagation. In: Chen, E., Gong, Y., Tie, Y. (eds) Advances in Multimedia Information Processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science(), vol 9916. Springer, Cham. https://doi.org/10.1007/978-3-319-48890-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-48890-5_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48889-9
Online ISBN: 978-3-319-48890-5
eBook Packages: Computer ScienceComputer Science (R0)