Abstract
This study compares the classification performance of a hybrid ensemble, which is called the global–local hybrid ensemble that employs both local and global learners against data manipulation ensembles including bagging and boosting variants. A comprehensive simulation study is performed on 46 UCI machine learning repository data sets using prediction accuracy and SAR performance metrics and along with rigorous statistical significance tests. Simulation results for comparison of classification performances indicate that global–local hybrid ensemble outperforms or ties with bagging and boosting ensemble variants in all cases. This suggests that the global–local ensemble has a more robust performance profile since its performance is less sensitive to variation with respect to the problem domain, or equivalently the data sets. This performance robustness is realized at the expense of increased complexity of the global–local ensemble since at least two types of learners, e.g. one global and another one local, must be trained. A complementary diversity analysis of global–local hybrid ensemble and base learners used for bagging and boosting ensembles on select data sets in the classifier projection space provides both an explanation and support for the performance related findings of this study.
Similar content being viewed by others
References
Aha D, Kibler D (1991) Instance-based learning algorithms. Mach Learn 6:37–66
Asuncion A, Newman DJ (2007) UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine. http://www.ics.uci.edu/~mlearn/MLRepository.html
Baumgartner D, Serpen G (2009) Large experiment and evaluation tool for WEKA classifiers. In: 5th international conference on data mining. Las Vegas, pp 340–346
Baumgartner D, Serpen G (2012) A design heuristic for hybrid ensembles. Intell Data Anal 16(2):233–246
Banfield RE, Hall LO, Bowyer KW, Bhadoria D, Kegelmeyer WP (2007) A comparison of decision tree ensemble creation techniques. IEEE Trans Pattern Anal Mach Intell 29(1):173–180
Battista B, Fumera G, Roli F (2010) Multiple classifier systems for robust classifier design in adversarial environments. Int J Mach Learn Cybern 1:27–41
Bian S, Wang W (2007) On diversity and accuracy of homogeneous and heterogeneous ensembles. Int J Hybrid Intell Syst 4:103–128
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Brown G, Wyatt J, Harris R, Yao X (2005) Diversity creation methods: a survey and categorisation. Inf Fusion 6:5–20
Caruana R, Niculescu-Mizil A, Crew G, Ksikes A (2004) Ensemble selection from libraries of models. In: Proceedings of the 21st international conference on machine learning, pp 137–144
Caruana R, Niculescu-Mizil A (2004) Data mining in metric space: an empirical analysis of supervised learning performance criteria. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining, Seattle, pp 69–78
Canuto AM, Abreu MC, Oliveira LM, Xavier JC, Santos AM (2007) Investigating the influence of the choice of the ensemble members in accuracy and diversity of selection-based and fusion-based methods for ensembles. Pattern Recognit Lett 28:472–486
Cawley GC, Talbot NL (n.d.) Miscellaneous Matlab Software. http://theoval.sys.uea.ac.uk/~gcc/matlab/default.html. Accessed January 2009
Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Dietterich TG (2000) Ensemble methods in machine learning. Lect Notes Comput Sci 1857:1–15
Dunn OJ (1961) Multiple comparisons among means. J Am Stat Assoc 56:52–64
Dzeroski S, Zenko B (2004) Is combining classifiers with stacking better than selecting the best one? Mach Learn 54:255–273
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Proceedings of the 13th international conference on machine learning, pp 148–156
Friedman M (1940) A comparison of alternative tests of significance for the problem of m rankings. Ann Math Stat 11:56–92
Hand DJ, Vinciotti V (2003) Local versus global models for classification problems: fitting models where it matters. Am Stat 57(2):124–131
Iman RL, Davenport JM (1980) Approximations of the critical region of the Friedman statistic. Commun Stat 571–595
Kotsiantis SB, Pintelas PE (2004) A hybrid decision support tool—using ensemble of classifiers. Int Conf Enterp Inf Syst (ICEIS) 2:448–456
Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship to ensemble accuracy. Mach Learn 51:181–207
Kuncheva LI (2003) That elusive diversity in classifier ensembles. Lect Notes Comput Sci 2652:1126–1138
Luengo J, Garcia S, Herra F (2007) A study on the use of statistical tests for experimentation with neural networks. In: Proceedings of the 9th international work-conference on artificial neural networks. Lecture notes on computer science, vol 4507, pp 72–79
Mitchell TM (1997) Machine learning. McGraw-Hill, NY
Opitz D, Maclin R (1999) Popular ensemble methods: an empirical study. J Artif Intell Res 11:169–198
Ott RL, Longnecker M (2001) An introduction to statistical methods and data analysis, 5th edn. Duxbury, Pacific Grove
Pekalska E, Duin RP, Skurichina M (2002) A discussion on the classifier projection space for classifier combining. In: Roli F, Kittler J (eds) 3rd international workshop on multiple classifier systems, MCS02, vol 2364. Springer, Cagliari, pp 137–148
Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45
Provost F, Domingos P (2003) Tree induction for probability-based ranking. Mach Learn 52(3):199–215
Quinlan JR (1996) Bagging, boosting, and C4.5. In: Proceedings of the 13th national conference on artificial intelligence, pp 725–730
Ricci F, Aha DW (1998) Error-correcting output codes for local learners. In: 10th european conference on machine learning, ECML. Springer, Berlin, pp 280–291
Sammon JW (1969) A nonlinear mapping for data structure analysis. IEEE Trans Comput 18:401–409
Seewald K, Furnkranz J (2001) An evaluation of grading classifiers. In: Proceedings of the 4th international conferences on advances in intelligent data analysis, pp 115–124
Seewald K (2002) How to make stacking better and faster while also taking care of an unknown weakness. In: Proceedings of the nineteenth international conference on machine learning, pp 554–561
Skalak D (1996) The sources of increased accuracy for two proposed boosting algorithms. In: AAAI ’96 workshop on integrating multiple learned models for improving and scaling machine learning algorithms
Tang EK, Suganthan PN, Yao X (2006) An analysis of diversity measures. Mach Learn 65:247–271
Witten H, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco
Wolpert DH (1992) Stacked generalization. Neural Netw 5(2):241–260
Yates WB, Patridge D (1996) Use of methodological diversity to improve neural network generalization. Neural Comput Appl 4(2):114–128
Zhiwen Y, Zhongkai D, Wong HS, Tan L (2010) Identifying protein kinase-specific phosphorylation sites based on the bagging-Adaboost ensemble approach. IEEE Trans Nanobiosci 9(2):132–143
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Baumgartner, D., Serpen, G. Performance of global–local hybrid ensemble versus boosting and bagging ensembles. Int. J. Mach. Learn. & Cyber. 4, 301–317 (2013). https://doi.org/10.1007/s13042-012-0094-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-012-0094-8