Abstract
In common binary classification scenarios, learning algorithms assume the presence of both positive and negative examples. Unfortunately, in many practical areas, only limited labeled positive examples and large amounts of unlabeled examples are available, but there are no negative examples. In such cases, the algorithm that only exploits positive and unlabeled examples is needed. Such learning is termed as positive and unlabeled (PU) learning. In this paper, a novel classifier called global and local learning classifier (GLLC) for PU learning is proposed. The advantages of GLLC are as follows: (1) both intrinsic geometric structure and accurate positive information of PU data are exploited from global learning. (2) The smoothness and manifold of data are reflected sufficiently from local learning. (3) The algorithm of GLLC has faster training speed because the linear equations are solved. (4) The experiments on both synthetic and real datasets verify the above opinions and show that the classification result of GLLC is much better than those popular methods, such as LUHC, Pulce, BSVM, NB and so on.
Similar content being viewed by others
References
Kılıc C, Tan M (2010) Positive unlabeled learning for deriving protein interaction networks. Network Modeling and Analysis in Health Informatics and Bioinformatics 1(3):87–102
Nguyen MN, Li XL, Ng SK (2011) Positive unlabeled learning for time series classification. In: Proceedings of the twenty-second international joint conference on artificial intelligence, pp 1421–1426
Li XL, Yu PS, Liu B, Ng SK (2009) Positive unlabeled learning for data stream classification. In: Proceedings of the ninth SIAM international conference on data mining (SDM’09), pp 257–268
Pan S, Zhang Y, Li X (2012) Dynamic classifier ensemble for positive unlabeled text stream classification. Knowl Inf Syst 33(2):267–287
Wang S, Chen ZY, Liu B (2016) Mining aspect-specific opinion using a holistic lifelong topic model. In: Proceedings of the international World Wide Web conference
Chen ZY, Ma NZ, Liu B (2015) Lifelong learning for sentiment classification. In: Proceedings of the 53st annual meeting of the association for computational linguistics, pp 26–31
Denis F (1998) PAC Learning from positive statistical queries. Lect Notes Comput Sci 1501:112–126
Muggleton S (1997) Learning from the positive data. machine learning, inductive logic programming. Lect Notes Comput Sci 1314:358–376
Liu B, Dai Y, Li XL, Lee WS, Yu PS (2003) Building text classifiers using positive and unlabeled examples. In: Proceedings of the 3rd IEEE International Conference on Data Mining, Melbourne, Florida, United States. IEEE. pp 179–188
Yu H, Han J, Chang KCC (2004) PEBL: Web Page classification without negative examples. IEEE Trans Knowl Data Eng 16(1):70–81
Vapnik VN (1995) The nature of statistical learning theory. Springer, Berlin
Christoffe M, Plessis D, Sugiyama M (2014) Semi-supervised learning of class balance under class-prior change by distribution matching. Neural Netw 50:110–119
Li XL, Liu B (2003) Learning to classify text using positive and unlabeled data. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence, Acapulco, vol 18. Springer, Mexico, pp 587–594
Fung GPC, Yu JX, Lu H, Yu PS (2006) Text classification without negative examples revisit. IEEE Trans Knowl Data Eng 18(1):6–20
Nguyen MN, Li XL, Ng SK (2011) Positive unlabeled learning for time series classification. In: Proceedings of international joint conference on artificial intelligence, IJCAI, pp 1421–1426
Ienco D, Pensa RG (2016) Positive and unlabeled learning in categorical data. Neurocomputing 196:113–124
Liu B, Lee WS, Yu PS et al (2002) Partially supervised classification of text documents. In: Proceedings of the 19th international conference on machine learning, pp 387–394
Schkopf B, John CP, John S, Alex J, Robert C (2001) Estimating the Support of a High-dimensional Distribution. Neural Comput 13(7):1443–1471
Zhu F, Ye N, Yu W, Xu S, Li GB (2014) Boundary detection and sample reduction for one-class support vector machines. Neurocomputing 123:166–173
Zhou K, Xue GR, Yang Q, Yu Y (2010) Learning with positive and unlabeled examples using topic-sensitive. PLSA, IEEE Trans Knowledge Data Eng 22(1):46–58
Zhang D, Lee WS (2005) A simple probabilistic approach to learning from positive and unlabeled examples. In: Proceedings of the 5th annual UK workshop on computational intelligence (UKCI), pp 83–87
Elkan C, Noto K (2008) Learning classifiers from only positive and unlabeled data. In: Proceedings of the 14th international conference on knowledge discovery and data mining, Las Vegas, vol 58(1). ACM, USA, pp 213–220
Luigi C, Charles E, Michele C (2010) Learning gene regulatory networks from only positive and unlabeled data. Bioinformatics 11(1):228–240
Lee WS, Liu B (2003) Learning with positive and unlabeled examples using weighted logistic regression. In: Proceedings of the 20th international conference on machine learning, Washington, vol 20. AAAI, United States, pp 448–455
Ke T, Yang B, Tan JY, Jing L (2012) Building high-performance classifiers on positive and unlabeled examples for text classification. Advances in Neural Networks ISNN, 2012. Lect Notes Comput Sci 7368:187–195
Shao YH, Chen WJ, Liu LM, Deng NY (2015) Laplacian unit-hyperplane learning from positive and unlabeled examples. Inf Sci 314:152–1687
Sellamanickam S, Garg P, Selvaraj SK (2011) A pairwise Ranking Based Approach to Learning with Positive and Unlabeled Examples. In Proceedings of the 20th ACM International Conference on Information and Knowledge Management, Glasgow, United Kingdom. ACM, New York, USA. 663–672
Suykens JAK (2000) Least squares support vector machines for classification and nonlinear modeling. Neural Network World 10(1–2):29–47
Chapelle O, Schokopf B, Zien A et al (2006) Semi-supervised learning. MIT press, Cambridge
Ke T, Tan JY, Yang B, Song LJ, Jing L (2014) A novel graph-based approach for transductive positive and unlabeled learning. J Comput Inf Syst 10(1):1–8
Zhang ZQ, Ke T, Deng NY, Tan JY (2014) Biased p-norm support vector machine for PU learning. Neurocomputing 136(136):256–261
Wang F (2010) A general learning framework using local and global regularization. Pattern Recogn 43:3120–3129
Blake CL, Merz CJ (1998) UCI Repository for Machine Learning Databases. <http://www.ics.uci.edu/mlearn/MLRepository.html>
Lin ZR (2016) LIBSVM. http://www.csie.ntu.edu.tw/~cjlin/libsvm
Liu B (2008) LPU package http://www.cs.uic.edu/~liub/LPU/LPU-download.html
USPS (1998) USPS Database. <http://www.cs.nyu.edu/roweis/data.html>
Acknowledgments
This work is supported by the youth innovative Foundation of Tianjin University of Science & Technology (2016LG30, 2016LG29).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ke, T., Jing, L., Lv, H. et al. Global and local learning from positive and unlabeled examples. Appl Intell 48, 2373–2392 (2018). https://doi.org/10.1007/s10489-017-1076-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-017-1076-z