Semi-supervised learning methods

被引：0
作者：
Liu, Jian-Wei [1 ]
Liu, Yuan [1 ]
Luo, Xiong-Lin [1 ]
机构：
[1] Research Institute of Automation, China University of Petroleum, Beijing
来源：
Jisuanji Xuebao/Chinese Journal of Computers | 2015年 / 38卷 / 08期
基金：
中国国家自然科学基金;
关键词：
Label; Labeled examples; Pair-wise constraints; Semi-supervised learning; Unlabeled instances;
D O I：
10.11897/SP.J.1016.2015.01592
中图分类号：
TP181 [自动推理、机器学习];
学科分类号：
摘要：
Semi-supervised learning is used to study how to improve performance in the presence of both examples and instances, and it has become a hot area of machine learning field. In view of the theoretical significance and practical value of semi-supervised learning, semi-supervised learning methods were reviewed in this paper systematically. Firstly, some concepts about semi-supervised learning were summarized, including definition of semi-supervised learning, development of research, assumptions relied on semi-supervised learning methods and classification of semi-supervised learning. Secondly, semi-supervised learning methods were detailed from four aspects, including classification, regression, clustering, and dimension reduction. Thirdly, theoretical analysis on semi-supervised learning was studied, and error bounds and sample complexity were given. Finally, the future research on semi-supervised learning was discussed. ©, 2015, Science Press. All right reserved.
引用
收藏
页码：1592 / 1617
页数：25
相关论文
共 187 条
[81]  
Rabiner L.R., A tutorial on hidden markov models and selected applications in speech recogntion, Proceedings of the IEEE, 77, 2, pp. 257-286, (1989)
[82]  
Yedidia J.S., Freeman W.T., Weiss Y., Generalized belief propagation, Proceedings of the Advances in Neural Information Processing Systems, pp. 689-695, (2000)
[83]  
Duda R.O., Hart P.E., Pattern Classification and Scene Analysis, (1973)
[84]  
Meir R., Empirical risk minimization versus maximum-likelihood estimation: A case study, Neural Computation, 7, 1, pp. 144-157, (1995)
[85]  
Chapelle O., Sindhwani V., Keerthi S.S., Optimazation techniques for semi-supervised support vector machines, The Journal of Machine Learning Research, 9, 6, pp. 203-233, (2008)
[86]  
Li Y.F., Zhou Z.H., Towards making unlabeled data never hurt, Proceedings of the 28th International Conference on Machine Learning, pp. 1081-1088, (2011)
[87]  
Fisher R.A., The use of multiple measurements in taxonomic problems, Annals of Eugenics, 7, 2, pp. 179-188, (1936)
[88]  
Baudat G., Anouar F., Generalized discriminant analysis using a kernel approach, Neural Computation, 12, 10, pp. 2385-2404, (2000)
[89]  
Grandvalet Y., Bengio Y., Semi-supervised learning by entropy minimization, Proceedings of the Advances in Neural Information Processing Systems 17, pp. 529-536, (2004)
[90]  
Zhu X., Lafferty J., Rosenfeld R., Semi-Supervised Learning with Graphs, (2005)
45678910111213