BCGAN: A CGAN-based over-sampling model using the boundary class for data balancing
- Authors
- Son, Minjae; Jung, Seungwon; Jung, Seungmin; Hwang, Eenjun
- Issue Date
- 9월-2021
- Publisher
- SPRINGER
- Keywords
- Imbalanced data; Conditional generative adversarial network (CGAN); Borderline minority class; Over-sampling
- Citation
- JOURNAL OF SUPERCOMPUTING, v.77, no.9, pp.10463 - 10487
- Indexed
- SCIE
SCOPUS
- Journal Title
- JOURNAL OF SUPERCOMPUTING
- Volume
- 77
- Number
- 9
- Start Page
- 10463
- End Page
- 10487
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/136436
- DOI
- 10.1007/s11227-021-03688-6
- ISSN
- 0920-8542
- Abstract
- A class imbalance problem occurs when a dataset is decomposed into one majority class and one minority class. This problem is critical in the machine learning domains because it induces bias in training machine learning models. One popular method to solve this problem is using a sampling technique to balance the class distribution by either under-sampling the majority class or over-sampling the minority class. So far, diverse over-sampling techniques have suffered from overfitting and noisy data generation problems. In this paper, we propose an over-sampling scheme based on the borderline class and conditional generative adversarial network (CGAN). More specifically, we define a borderline class based on the minority class data near the majority class. Then, we generate data for the borderline class using the CGAN for data balancing. To demonstrate the performance of the proposed scheme, we conducted various experiments on diverse imbalanced datasets. We report some of the results.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.