Abstract
Scalability has become an increasingly critical issue for successful data mining applications in the ”big data” era in which extremely huge data sets render traditional learning algorithms infeasible. Among various approaches to scalable learning, sampling techniques can be exploited to address the issue of scalability. This paper presents our study on applying a newly developed sampling-based boosting learning method for multi-class (non-binary) classification. Preliminary experimental results using bench-mark data sets from the UC-Irvine ML data repository confirm the efficiency and competitive prediction accuracy of the proposed adaptive boosting method for the multi-class classification task. We also show a formulation of using a single ensemble of non-binary base classifiers with adaptive sampling for multi-class problems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chernoff, H.: A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Statist. 23, 493–507 (1952)
Zhu, J., Rosset, S., Zou, H., Hastie, T.: Multi-class AdaBoost. Statistics and its Interface 2, 349–360 (2009)
Friedman, J., Hastie, T., Tibshirani, R.: Additivel Logistic Regression: A Statistical View of Boosting. Annals of Statistics 28, 337–407 (2000)
Mukherjee, I., Shapire, R.: A Theory of Multiclass Boosting. Journal of Machine Learning Research 14, 437–497 (2013)
Sun, P., Reid, M.D., Zhou, J.: AOSO-LogitBoost: Adaptive one-vs-one LogitBoost for Multi-class Problem. In: International Conference on Machine Learning (ICML) (2012)
Kegl, B.: The Return of AdaBoost.MH: Multi-class Hamming Trees. arXiv:1312.6086 [cs.LG] (preprint)
Freund, Y., Schapire, R.: Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting. J. of Computer and System Sciences 55(1), 119–139 (1997)
Schapire, R., Singer, Y.: Improved Boosting Algorithms using Confidence-rated Prediction. Machine Learning 37(3), 297–336 (1999)
Allwein, E., Schapire, R., Singer, Y.: Reducing Multiclass to Binary: A Unifying Approach for Margin Classifier. Journal of Machine Learning Research 1, 113–141 (2000)
Chen, J., Xu, J.: Sampling Adaptively using the Massart Inequality for Scalable Learning by Boosting. In: Proceedings of ICMLA Workshop on Machine Learning Algorithms, Systems and Applications, Miami, Florida (December 2013)
Chen, J.: Scalable Ensemble Learning by Adaptive Sampling. In: Proceedings of International Conference on Machine Learning and Applications (ICMLA), pp. 622–625 (December 2012)
Chen, J., Chen, X.: A New Method for Adaptive Sequential Sampling for Learning and Parameter Estimation. In: Kryszkiewicz, M., Rybinski, H., Skowron, A., Raś, Z.W. (eds.) ISMIS 2011. LNCS, vol. 6804, pp. 220–229. Springer, Heidelberg (2011)
Chen, X.: A new framework of multistage parametric inference. In: Proceeding of SPIE Conference, Orlando, Florida, vol. 7666, pp. 76660R1–76660R12 (April 2010)
Domingo, C., Watanabe, O.: Scaling up a boosting-based learner via adaptive sampling. In: Terano, T., Liu, H., Chen, A.L.P. (eds.) PAKDD 2000. LNCS, vol. 1805, pp. 317–328. Springer, Heidelberg (2000)
Domingo, C., Watanabe, O.: Adaptive sampling methods for scaling up knowledge discovery algorithms. In: Proceedings of 2nd Int. Conference on discovery Science, Japan (December 1999)
Frey, J.: Fixed-width sequential confidence intervals for a proportion. The American Statistician 64, 242–249 (2010)
Hoeffding, W.: Probability inequalities for sums of bounded variables. J. Amer. Statist. Assoc. 58, 13–29 (1963)
Lipton, R., Naughton, J., Schneider, D.A., Seshadri, S.: Efficient sampling strategies for relational database operations. Theoretical Computer Science 116, 195–226 (1993)
Lipton, R., Naughton, J.: Query size estimation by adaptive sampling. Journal of Computer and System Sciences 51, 18–25 (1995)
Lynch, J.F.: Analysis and application of adaptive sampling. Journal of Computer and System Sciences 66, 2–19 (2003)
Watanabe, O.: Sequential sampling techniques for algorithmic learning theory. Theoretical Computer Science 348, 3–14 (2005)
Hanneke, S.: A bound on the label complexity of agnostic active learning. In: Corvallis, O.R. (ed.) Proceedings of the 24th Int. Conf. on Machine Learning (2007)
Watanabe, O.: Simple sampling techniques for discovery sciences. IEICE Trans. Inf. & Sys. ED83-D, 19–26 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Chen, J. (2014). A Scalable Boosting Learner for Multi-class Classification Using Adaptive Sampling. In: Ślȩzak, D., Schaefer, G., Vuong, S.T., Kim, YS. (eds) Active Media Technology. AMT 2014. Lecture Notes in Computer Science, vol 8610. Springer, Cham. https://doi.org/10.1007/978-3-319-09912-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-09912-5_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09911-8
Online ISBN: 978-3-319-09912-5
eBook Packages: Computer ScienceComputer Science (R0)