Ad-RuLer: A Novel Rule-Driven Data Synthesis Technique for Imbalanced Classification
Source abstract
Abstract
When classifiers face imbalanced class distributions, they often misclassify minority class samples, consequently diminishing the predictive performance of machine learning models. Existing oversampling techniques predominantly rely on the selection of neighboring data via interpolation, with less emphasis on uncovering the intrinsic patterns and relationships within the data. In this research, we present the usefulness of an algorithm named RuLer to deal with the problem of classification with imbalanced data. RuLer is a learning algorithm initially designed to recognize new sound patterns within the context of the performative artistic practice known as live coding. This paper demonstrates that this algorithm, once adapted (Ad-RuLer), has great potential to address the problem of oversampling imbalanced data. An extensive comparison with other mainstream oversampling algorithms (SMOTE, ADASYN, Tomek-links, Borderline-SMOTE, and KmeansSMOTE), using different classifiers (logistic regression, random forest, and XGBoost) is performed on several real-world datasets with different degrees of data imbalance. The experiment results indicate that Ad-RuLer serves as an effective oversampling technique with extensive applicability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Imbalanced Data Classification Techniques · Machine Learning and Data Classification · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Soft Computing Research Group at Intelligent Data Science, Artificial Intelligence Research Center, Universitat Politècnica de Catalunya, 08003 Barcelona, Spain
References (47)
Show source-provided references
1. Financial fraud detection using naive bayes algorithm in highly imbalance data set10.1080/09720529.2021.1969733 ↗
2. Gu, Q., Cai, Z., Zhu, L., and Huang, B. (2008, January 20–22). Data mining on imbalanced data sets. Proceedings of the 2008 International Conference on Advanced Computer Theory and Engineering, Phuket, Thailand.10.1109/ICACTE.2008.26 ↗
3. Jiang, Z., Pan, T., Zhang, C., and Yang, J. (2021). A new oversampling method based on the classification contribution degree. Symmetry, 13.10.3390/sym13020194 ↗
4. Gonzalez-Cuautle, D., Hernandez-Suarez, A., Sanchez-Perez, G., Toscano-Medina, L.K., Portillo-Portillo, J., Olivares-Mercado, J., Perez-Meana, H.M., and Sandoval-Orozco, A.L. (2020). Synthetic minority oversampling technique for optimizing classification tasks in botnet and intrusion-detection-system datasets. Appl. Sci., 10.10.3390/app10030794 ↗
5. A fast network intrusion detection system using adaptive synthetic oversampling and LightGBM10.1016/j.cose.2021.102289 ↗
6. Guzmán-Ponce, A., Valdovinos, R.M., Sánchez, J.S., and Marcial-Romero, J.R. (2020). A new under-sampling method to face class overlap and imbalance. Appl. Sci., 10.10.3390/app10155164 ↗
7. Multi-granularity relabeled under-sampling algorithm for imbalanced data10.1016/j.asoc.2022.109083 ↗
8. Uncertainty based under-sampling for learning naive bayes classifiers under imbalanced data sets10.1109/ACCESS.2019.2961784 ↗
9. Network intrusion detection combined hybrid sampling with deep hierarchical network10.1109/ACCESS.2020.2973730 ↗
10. Xu, Z., Shen, D., Nie, T., and Kou, Y. (2020). A hybrid sampling algorithm combining M-SMOTE and ENN based on Random forest for medical imbalanced data. J. Biomed. Informatics, 107.10.1016/j.jbi.2020.103465 ↗
11. HCBST: An efficient hybrid sampling technique for class imbalance problems
12. Improving interpolation-based oversampling for imbalanced data learning10.1016/j.knosys.2019.06.034 ↗
13. FROTE: Feedback rule-driven oversampling for editing models
14. Paz, I. (2021). On-the-Fly Synthesizer Programming with Rule Learning. [Ph.D. Thesis, Universitat Politècnica de Catalunya—BarcelonaTech].
15. KNNOR: An oversampling technique for imbalanced datasets10.1016/j.asoc.2021.108288 ↗
16. Synthetic minority oversampling technique for multiclass imbalance problems10.1016/j.patcog.2017.07.024 ↗
17. Neighbourhood-based undersampling approach for handling imbalanced and overlapped data10.1016/j.ins.2019.08.062 ↗
18. Cost-sensitive and hybrid-attribute measure multi-decision tree over imbalanced data sets10.1016/j.ins.2017.09.013 ↗
19. A cost-sensitive deep belief network for imbalanced classification10.1109/TNNLS.2018.2832648 ↗
20. Cost sensitive active learning using bidirectional gated recurrent neural networks for imbalanced fault diagnosis10.1016/j.neucom.2020.04.075 ↗
21. A survey on addressing high-class imbalance in big data10.1186/s40537-018-0151-6 ↗
22. Addressing the curse of imbalanced training sets: One-sided selection
23. Cluster-based under-sampling approaches for imbalanced data distributions10.1016/j.eswa.2008.06.108 ↗
24. Clustering-based undersampling in class-imbalanced data10.1016/j.ins.2017.05.008 ↗
25. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
26. Han, H., Wang, W.Y., and Mao, B.H. (2005, January 23–26). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. Proceedings of the Advances in Intelligent Computing: International Conference on Intelligent Computing, ICIC 2005, Hefei, China.10.1007/11538059_91 ↗
27. MWMOTE–majority weighted minority oversampling technique for imbalanced data set learning10.1109/TKDE.2012.232 ↗
28. Zhang, X., Ma, D., Gan, L., Jiang, S., and Agam, G. (2016, January 24–28). Cgmos: Certainty guided minority oversampling. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, Indianapolis, IN, USA.10.1145/2983323.2983789 ↗
29. Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE10.1016/j.ins.2018.06.056 ↗
30. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.
31. An alternative SMOTE oversampling strategy for high-dimensional datasets10.1016/j.asoc.2018.12.024 ↗
32. ACO Resampling: Enhancing the performance of oversampling methods for class imbalance classification10.1016/j.knosys.2020.105818 ↗
33. CDBH: A clustering and density-based hybrid approach for imbalanced data classification10.1016/j.eswa.2020.114035 ↗
34. Ai-jun, L., and Peng, Z. (2020, January 26–28). Research on Unbalanced Data Processing Algorithm Base Tomeklinks-Smote. Proceedings of the 2020 3rd International Conference on Artificial Intelligence and Pattern Recognition, Xiamen China.10.1145/3430199.3430222 ↗
35. Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 15–20). Class-balanced loss based on effective number of samples. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
36. Mullick, S.S., Datta, S., and Das, S. (November, January 27). Generative adversarial minority oversampling. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
37. Kim, J., Jeong, J., and Shin, J. (2020, January 13–19). M2m: Imbalanced classification via major-to-minor translation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01391 ↗
38. Cui, J., Zhong, Z., Liu, S., Yu, B., and Jia, J. (2021, January 11–17). Parametric contrastive learning. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00075 ↗
39. Wang, P., Han, K., Wei, X.S., Zhang, L., and Wang, L. (2021, January 20–25). Contrastive learning based hybrid networks for long-tailed image classification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00100 ↗
40. Shi, M., Tang, Y., Zhu, X., Wilson, D., and Liu, J. (2020, January 11–17). Multi-class imbalanced graph convolutional network learning. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), Yokohama, Japan.10.24963/ijcai.2020/398 ↗
41. Zhao, T., Zhang, X., and Wang, S. (2021, January 8–12). Graphsmote: Imbalanced node classification on graphs with graph neural networks. Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Virtual.10.1145/3437963.3441720 ↗
42. Qu, L., Zhu, H., Zheng, R., Shi, Y., and Yin, H. (2021, January 14–18). Imgagn: Imbalanced network embedding via generative adversarial graph networks. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual.10.1145/3447548.3467334 ↗
43. Huynh, T., Nibali, A., and He, Z. (2022). Semi-supervised learning for medical image classification using imbalanced training data. Comput. Methods Programs Biomed., 216.10.1016/j.cmpb.2022.106628 ↗
44. Hyun, M., Jeong, J., and Kwak, N. (2020). Class-imbalanced semi-supervised learning. arXiv.
45. Fuzzy rule-based oversampling technique for imbalanced and incomplete data learning10.1016/j.knosys.2018.05.044 ↗
46. Paz, I., Nebot, À., Mugica, F., and Romero, E. (2020). On-The-Fly Syntheziser Programming with Fuzzy Rule Learning. Entropy, 22.10.3390/e22090969 ↗
47. Visualizing data using t-SNE