Semi-supervised Classification Based on Smooth Graphs
In semi-supervised classification, labels smoothness and cluster assumption are the key point of many successful methods. In graph-based semi-supervised classification, graph representations of the data are quite important. Different graph representations can affect the classification results greatly. Considering the two assumptions and graph representations, we propose a novel method to build a better graph for semi-supervised classification. The graph in our method is called m-step Markov random walk graph (mMRW graph). The smoothness of this graph can be controlled by a parameter m. We believe that a relatively much smoother graph will benefit transductive learning. We also discuss some benefits brought by our smooth graphs. A cluster cohesion based parameter learning method can be efficiently applied to find a proper m. Experiments on artificial and real world dataset indicate that our method has a superior classification accuracy over several state-of-the-art methods.
KeywordsRandom Walk Unlabeled Data Neural Information Processing System Connection Matrix Cluster Kernel
Unable to display preview. Download preview PDF.
- 1.Chapelle, O., Weston, J., Schölkopf, B.: Cluster Kernels for Semi-Supervised Learning. In: Advances in Neural Information Processing Systems 15, pp. 585–592. MIT Press, Cambridge (2003)Google Scholar
- 2.Chapelle, O., Zien, A.: Semi-Supervised Classification by Low Density Separation. In: Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, pp. 57–64 (2005)Google Scholar
- 5.Seeger, M.: Learning with labeled and unlabeled data. Technical report, Edinburgh University (2000)Google Scholar
- 6.Shanbhag, D.N., Rao, C.R. (eds.): Handbook of Stochastic, vol. 19. Elsevier Science, Amsterdam (2001)Google Scholar
- 7.Szummer, M., Jaakkola, T.: Partially labeled classification with Markov random walks. Neural Information Processing. Systems (NIPS) 14 (2001)Google Scholar
- 8.Zhou, D., et al.: Learning with local and global consistency. In: Advances in Neural Information Processing System 16 (2004)Google Scholar
- 9.Zhu, X., Lafferty, J., Ghahramani, Z.: Semi-Supervised Learning Using Gaussian Fields and Harmonic Function. In: Proceedings of The Twentieth International Conference on Machine Learning (2003)Google Scholar
- 10.Zhu, X.: Semi-Supervised Learning with Graphs. Doctoral Thesis. CMU-LTI-05-192, Carnegie Mellon University (2005)Google Scholar