A novel oversampling method based on Wasserstein CGAN for imbalanced classification
Abstract Class imbalance is a crucial challenge in classification tasks, and in recent years, with the advancements in deep learning, research on oversampling techniques based on GANs has proliferated. These techniques have proven to be excellent in addressing the class imbalance issue by capturing...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-02-01
|
| Series: | Cybersecurity |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42400-024-00290-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571593145974784 |
|---|---|
| author | Hongfang Zhou Heng Pan Kangyun Zheng Zongling Wu Qingyu Xiang |
| author_facet | Hongfang Zhou Heng Pan Kangyun Zheng Zongling Wu Qingyu Xiang |
| author_sort | Hongfang Zhou |
| collection | DOAJ |
| description | Abstract Class imbalance is a crucial challenge in classification tasks, and in recent years, with the advancements in deep learning, research on oversampling techniques based on GANs has proliferated. These techniques have proven to be excellent in addressing the class imbalance issue by capturing the distributional features of minority samples during training and generating high-quality new samples. However, oversampling methods based on GANs may suffer from gradient vanishing, resulting in mode collapse, and produce noise and boundary-blurring issues when generating new samples. This paper proposes a novel oversampling method based on a conditional GAN (CGAN) incorporating Wasserstein distance. It generates an initial balanced dataset from minority class samples using the CGAN oversampling approach and then uses a noise and boundary recognition method based on K-means and $$k$$ k nearest neighbors algorithm to address the noise and boundary-blurring issues. The proposed method generates new samples that are highly consistent with the original sample distribution and effectively solves the problems of noise data and class boundary blurring. Experimental results on multiple public datasets show that the proposed method achieves significant improvements in evaluation metrics such as Recall, F1_score, G-mean, and AUC. |
| format | Article |
| id | doaj-art-7b7a7c02936b4994b4cd381fbd42f54d |
| institution | Kabale University |
| issn | 2523-3246 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Cybersecurity |
| spelling | doaj-art-7b7a7c02936b4994b4cd381fbd42f54d2025-02-02T12:30:05ZengSpringerOpenCybersecurity2523-32462025-02-018112010.1186/s42400-024-00290-0A novel oversampling method based on Wasserstein CGAN for imbalanced classificationHongfang Zhou0Heng Pan1Kangyun Zheng2Zongling Wu3Qingyu Xiang4School of Computer Science and Engineering, Xi’an University of TechnologySchool of Computer Science and Engineering, Xi’an University of TechnologySchool of Computer Science and Engineering, Xi’an University of TechnologySchool of Computer Science and Engineering, Xi’an University of TechnologySchool of Chemical Engineering, Northwest UniversityAbstract Class imbalance is a crucial challenge in classification tasks, and in recent years, with the advancements in deep learning, research on oversampling techniques based on GANs has proliferated. These techniques have proven to be excellent in addressing the class imbalance issue by capturing the distributional features of minority samples during training and generating high-quality new samples. However, oversampling methods based on GANs may suffer from gradient vanishing, resulting in mode collapse, and produce noise and boundary-blurring issues when generating new samples. This paper proposes a novel oversampling method based on a conditional GAN (CGAN) incorporating Wasserstein distance. It generates an initial balanced dataset from minority class samples using the CGAN oversampling approach and then uses a noise and boundary recognition method based on K-means and $$k$$ k nearest neighbors algorithm to address the noise and boundary-blurring issues. The proposed method generates new samples that are highly consistent with the original sample distribution and effectively solves the problems of noise data and class boundary blurring. Experimental results on multiple public datasets show that the proposed method achieves significant improvements in evaluation metrics such as Recall, F1_score, G-mean, and AUC.https://doi.org/10.1186/s42400-024-00290-0CGANImbalanced dataClassificationOversamplingK-means$$k$$ k nearest neighbors |
| spellingShingle | Hongfang Zhou Heng Pan Kangyun Zheng Zongling Wu Qingyu Xiang A novel oversampling method based on Wasserstein CGAN for imbalanced classification Cybersecurity CGAN Imbalanced data Classification Oversampling K-means $$k$$ k nearest neighbors |
| title | A novel oversampling method based on Wasserstein CGAN for imbalanced classification |
| title_full | A novel oversampling method based on Wasserstein CGAN for imbalanced classification |
| title_fullStr | A novel oversampling method based on Wasserstein CGAN for imbalanced classification |
| title_full_unstemmed | A novel oversampling method based on Wasserstein CGAN for imbalanced classification |
| title_short | A novel oversampling method based on Wasserstein CGAN for imbalanced classification |
| title_sort | novel oversampling method based on wasserstein cgan for imbalanced classification |
| topic | CGAN Imbalanced data Classification Oversampling K-means $$k$$ k nearest neighbors |
| url | https://doi.org/10.1186/s42400-024-00290-0 |
| work_keys_str_mv | AT hongfangzhou anoveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT hengpan anoveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT kangyunzheng anoveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT zonglingwu anoveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT qingyuxiang anoveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT hongfangzhou noveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT hengpan noveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT kangyunzheng noveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT zonglingwu noveloversamplingmethodbasedonwassersteincganforimbalancedclassification AT qingyuxiang noveloversamplingmethodbasedonwassersteincganforimbalancedclassification |