Abstract
Ensemble learning consists of combining the prediction of different learners to obtain a final output. One key step for their success is the diversity among the learners. In this paper, we propose to reach the diversity in terms of the classification complexity by guiding the sampling of instances in the Bagging algorithm with complexity measures. The proposed Complexity-driven Bagging algorithm complements the classic Bagging algorithm by considering training samples of different complexity to cover the complexity space. Besides, the algorithm admits any complexity measure to guide the sampling. The proposal is tested in 28 real datasets and for a total of 9 complexity measures, providing satisfactory and promising results and revealing that training with samples of different complexity, ranging from easy to hard samples, is the best strategy when sampling based on complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Breiman, L.: Bagging predictors. Mach. Learn. 24, 123–140 (1996)
Dietterich, T.G.: Ensemble methods in machine learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45014-9_1
Dua, D., Graff, C.: UCI machine learning repository (2017). https://archive.ics.uci.edu/ml
Freund, Y., Schapire, R.E., et al.: Experiments with a new boosting algorithm. In: ICML, vol. 96, pp. 148–156 (1996)
Hansen, L.K., Salamon, P.: Neural network ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 12(10), 993–1001 (1990)
Ho, T.K., Basu, M.: Complexity measures of supervised classification problems. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 289–300 (2002)
Kabir, A., Ruiz, C., Alvarez, S.A.: Mixed bagging: a novel ensemble learning framework for supervised classification based on instance hardness. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 1073–1078. IEEE (2018)
Lancho, C., Martín De Diego, I., Cuesta, M., Acena, V., Moguerza, J.M.: Hostility measure for multi-level study of data complexity. Appl. Intell. 53, 1–24 (2022)
Lorena, A.C., Garcia, L.P., Lehmann, J., Souto, M.C., Ho, T.K.: How complex is your classification problem? a survey on measuring classification complexity. ACM Comput. Surv. (CSUR) 52(5), 1–34 (2019)
Monteiro, M., Jr., Britto, A.S., Jr., Barddal, J.P., Oliveira, L.S., Sabourin, R.: Exploring diversity in data complexity and classifier decision spaces for pool generation. Inf. Fusion 89, 567–587 (2023)
Sagi, O., Rokach, L.: Ensemble learning: a survey. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 8(4), e1249 (2018)
Sleeman IV, W.C., Krawczyk, B.: Bagging using instance-level difficulty for multi-class imbalanced big data classification on spark. In: 2019 IEEE International Conference on Big Data, pp. 2484–2493. IEEE (2019)
Smith, M.R., Martinez, T., Giraud-Carrier, C.: An instance level analysis of data complexity. Mach. Learn. 95(2), 225–256 (2014)
Walmsley, F.N., Cavalcanti, G.D., Oliveira, D.V., Cruz, R.M., Sabourin, R.: An ensemble generation method based on instance hardness. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2018)
Acknowledgements
This research is supported by grants from Rey Juan Carlos University (Ref: C1PREDOC2020) and the Spanish Ministry of Science and Innovation, under the Knowledge Generation Projects program: XMIDAS (Ref: PID2021-122640OB-100). A. C. Lorena would also like to thank the financial support of the FAPESP research agency (grant 2021/06870-3).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lancho, C., C. P. de Souto, M., Lorena, A.C., Martín de Diego, I. (2023). Complexity-Driven Sampling for Bagging. In: Quaresma, P., Camacho, D., Yin, H., Gonçalves, T., Julian, V., Tallón-Ballesteros, A.J. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404. Springer, Cham. https://doi.org/10.1007/978-3-031-48232-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-48232-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48231-1
Online ISBN: 978-3-031-48232-8
eBook Packages: Computer ScienceComputer Science (R0)