In locally linear embedding framework, a semi-supervised manifold learning method based on 2-fold weights is proposed. The basic idea is not only to preserve intra-class local information in the processing of dimensionality reduction but also to predict the label of a data point according to its neighbours. Different from existing approaches, our method finds the k-nearest neighbours of each point in k-multiplicity minimum spanning trees (MST) instead of the complete Euclidean graph. Two-fold weights are learned. One is the reconstruction weights for finding the embedding. The other is the derivative weights for class label propagation. The experimental results on synthetic and real data, multi-class data sets demonstrate the effectiveness of the proposed approach.
Inspec keywords: learning (artificial intelligence); trees (mathematics); data reduction; computational geometry
Other keywords:
Subjects: Knowledge engineering techniques; Combinatorial mathematics; Computational geometry; Graphics techniques
References
-
-
1)
- G. Baudat , F. Anoua . Generalized discriminant analysis using a kernel approach. Neural Comput. , 10 , 2385 - 2404
-
2)
- Y. Li . Building k-connected neighborhood graphs for isometric data embedding. IEEE Trans. Pattern Anal. Mach. Intell. , 10 , 827 - 831
-
3)
- D. Meng , L. Yee , T. Fung , Z. Xu . Nonlinear dimensionality reduction of data lying on the multicluster manifold. IEEE Trans. Syst. Man Cybern.- Part B: Cybern. , 4 , 1111 - 1122
-
4)
- Blum, A., Mitchell, T.: `Combining labeled and unlabeled sata with Co-training', Proc. 11th Annual Conf. on Computational Learning Theory, 1998, p. 92–100.
-
5)
- J. Venna , S. Kaski . Local multidimensional scaling. Neural Netw. , 889 - 899
-
6)
- Y. Li . Building k edge-disjoint spanning trees of minimum total length for isometric data embedding. IEEE Trans. Pattern Anal. Mach. Intell. , 10 , 1680 - 1683
-
7)
- Y. Wang , Y. Jiang , Y. Wu , Z.-H. Zhou . Spectral clustering on multiple manifolds. IEEE Trans. Neural Netw. , 7 , 1149 - 1161
-
8)
- S. Mika , G. Rätsch , J. Weston , B. Schölkopf , K.-R. Muller , Y.-H. Hu , J. Larsen , E. Wilson , S. Douglas . (1999) Fisher discriminant analysis with kernels, Proc. neural networks for signal processing IX.
-
9)
- T. Cox , M. Cox . (2001) Multidimensional scaling.
-
10)
- P. Belhumeur , J. Hespanha , D. Kriegman . Eigenfaces vs fusherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 711 - 720
-
11)
- Nigam, K.: `Using unlabeled data to improve text classification', 2001, PhD, Carnegie Mellon University, Department of Computer Science.
-
12)
- I. Joliffe . (1986) Principal component analysis.
-
13)
- S. Li , Z.Q. Zhang . FloatBoost learning and statistical face detection. IEEE Trans. Pattern Anal. Mach. Intell. , 1112 - 1123
-
14)
- J.B. Tenenbaum , V. de Silva , J.C. Langford . A global geometric framework for nonlinear dimensionality reduction. Science , 5500 , 2319 - 2323
-
15)
- Joachims, T.: `Transductive inference for text classification using support vector machines', Proc. 16th Int. Conf. on Machine Learning, 1999, p. 200–209.
-
16)
- Rosenberg, C., Hebert, M., Schneiderman, H.: `Semi-supervised self-training of object detection models', Proc. Seventh IEEE Workshops Application of Computer Vision, 2005, p. 29–36.
-
17)
- Y. Li . Building k-edge-connected neighborhood graphs for distance-based data projection. Pattern Recognit. Lett. , 13 , 2015 - 2021
-
18)
- Zhu, X.: `Semi-supervised learning literature survey', Technical Report 1530, Department of Computer Sciences, University of Wisconsin Madison, 2006.
-
19)
- J. Wang , F. Wang , C. Zhang , H. Shen , L. Quan . Linear neighborhood propagation and its applications. IEEE Trans. Pattern Anal. Mach. Intell. , 9 , 1600 - 1615
-
20)
- Torki, M., Elgammal, A., Lee, C.S.: `Learning a joint manifold representation from multiple data sets', ICPR, 2010, p. 1068–1071.
-
21)
- V. Roth , V. Steinhage , S.A. Solla , T.K. Leen , K.-R. Müller . (1999) Nonlinear discriminant analysis using kernel functions, Advances in neural information processing systems.
-
22)
- Saul, L., Roweis, S.: `Think globally, fit locally: unsupervised learning of nonlinear manifolds', Technical Report MS CIS-02-18, University of Pennsylvania, 2002.
-
23)
- Z. Zhou , M. Li . Semi-supervised regression with co-training style algorithms. IEEE Trans. Knowl. Data Eng. , 11 , 1417 - 1493
-
24)
- D. Zhou , O. Bousquet , T.N. Lal , J. Weston , B. Scho lkopf . (2004) Learning with local and global consistency, Advances in neural information processing systems.
-
25)
- Zhu, X., Ghahramani, Z., Lafferty, J.: `Semi-supervised learning using Gaussian fields and harmonic functions', Proc. 20th Int. Conf. on Machine Learning, 2003, p. 912–919.
-
26)
- M. Culp , G. Michailidis . Graph-based semi supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. , 1 , 174 - 179
-
27)
- Joachims, T.: `Transductive learning via spectral graph partitioning', Proc. 20th Int. Conf. Machine Learning, 2003, p. 290–297.
-
28)
- Nene, S., Nayar, S., Murase, H.: `Columbia object image library (COIL-20)', Technical Report CUCS-005-96, 5 February 1996.
-
29)
- S.T. Roweis , L.K. Saul . Nonlinear dimensionality reduction by locally linear embedding. Science. , 5500 , 2323 - 2326
-
30)
- Fujino, A., Ueda, N., Saito, K.: `A hybrid generative discriminative approach to semi-supervised classifier design', Proc. 20th Artificial Intelligence, 2005, p. 764–769.
-
1)
Related content