Abstract
In this work, we investigate the impact of class imbalance on the accuracy and diversity of synthetic samples generated by conditional generative adversarial networks (CGAN) models. Though many studies utilizing GANs have seen extraordinary success in producing realistic image samples, these studies generally assume the use of well-processed and balanced benchmark image datasets, including MNIST and CIFAR-10. However, well-balanced data is uncommon in real world applications such as detecting fraud, diagnosing diabetes, and predicting solar flares. It is well known that when class labels are not distributed uniformly, the predictive ability of classification algorithms suffers significantly, a phenomenon known as the “class-imbalance problem.” We show that the imbalance in the training set can also impact sample generation of CGAN models. We utilize the well known MNIST datasets, controlling the imbalance ratio of certain classes within the data through sampling. We are able to show that both the quality and diversity of generated samples suffer in the presence of class imbalances and propose a novel framework named Two-stage CGAN to produce high-quality synthetic samples in such cases. Our results indicate that the proposed framework provides a significant improvement over typical oversampling and undersampling techniques utilized for class imbalance remediation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, G., Jafari, A.H.: Enhanced balancing GAN: minority-class image generation. Neural Comput. Appl. 1–10 (2021). https://doi.org/10.1007/s00521-021-06163-8
Mariani, G., Scheidegger, F., Istrate, R., Bekas, C., Malossi, C.: Bagan: data augmentation with balancing GAN, arXiv preprintar Xiv:1803.09655 (2018)
Ahmadzadeh, A., et al.: Challenges with extreme class-imbalance and temporal coherence: a study on solar flare data. In: 2019 IEEE International Conference on Big Data (Big Data), pp. 1423–1431 (2019). https://doi.org/10.1109/BigData47090.2019.9006505
Ahmadzadeh, A., et al.: How to train your flare prediction model: revisiting robust sampling of rare events. Astrophys. J. Supplement Ser. 254(2), 23 (2021). https://doi.org/10.3847/1538-4365/abec88
Angryk, R.A., et al.: Multivariate time series dataset for space weather data analytics. Sci. Data 7(1) (2020). https://doi.org/10.1038/s41597-020-0548-x
Douzas, G., Bacao, F., Last, F.: Improving imbalanced learning through a heuristic oversampling method based on k-means and smote. Inf. Sci. 465, 1–20 (2018)
Wen, Q., et al.: Time series data augmentation for deep learning: a survey, arXiv preprintar Xiv:2002.12478 (2020)
Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002). https://doi.org/10.1613/jair.953
Douzas, G., Bacao, F.: Effective data generation for imbalanced learning using conditional generative adversarial networks. Exp. Syst. Appl. 91, 464–471 (2018). https://www.sciencedirect.com/science/article/pii/S0957417417306346
Goodfellow, et al.: Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, ser. NIPS 2014. Cambridge, MA, USA, MIT Press, pp. 2672–2680 (2014). https://dl.acm.org/doi/10.5555/2969033.2969125
Chen, Y., Kempton, D.J., Ahmadzadeh, A., Angryk, R.A.: Towards synthetic multivariate time series generation for flare forecasting. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2021. LNCS (LNAI), vol. 12854, pp. 296–307. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87986-0_26
Chen, K., Lu, B.-L., Kwok, J.T.: Efficient classification of multi-label and imbalanced data using min-max modular classifiers. In: The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 1770–1775. IEEE (2006)
Tahir, M.A., Kittler, J., Yan, F.: Inverse random under sampling for class imbalance problem and its application to multi-label classification. Pattern Recogn. 45(10), 3738–3750 (2012). https://www.sciencedirect.com/science/article/pii/S0031320312001471
Sun, Y., Kamel, M.S., Wong, A.K., Wang, Y.: Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 40(12), 3358–3378 (2007)
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: An overview. IEEE Sig. Process. Mag. 35(1), 53–65 (2018). https://doi.org/10.1109/MSP.2017.2765202
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70. JMLR.org, pp. 214–223 (2017). https://dl.acm.org/doi/10.5555/3305381.3305404
Radford, A., et al.: Unsupervised representation learning with deep convolutional generative adversarial networks, CoRR, vol. abs/1511.06434 (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014). http://arxiv.org/abs/1411.1784
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2016, pp. 2818–2826 (2016)
Brownlee, J.: Generative adversarial networks with python: deep learning generative models for image synthesis and image translation. Machine Learning Mastery (2019). https://books.google.com/books?id=YBimDwAAQBAJ
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). software available from tensorflow.org
Acknowledgment
This project has been supported in part by funding from the Division of Advanced Cyberinfrastructure within the Directorate for Computer and Information Science and Engineering, the Division of Atmospheric & Geospace Sciences within the Directorate for Geosciences, under NSF awards #1931555 and # 1936361. It has also been supported by NASA’s Space Weather Science Application Research-to-Operations-to-Research program grant #80NSSC22K0272.
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
Chen, Y., Kempton, D.J., Angryk, R.A. (2023). Examining Effects of Class Imbalance on Conditional GAN Training. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2023. Lecture Notes in Computer Science(), vol 14125. Springer, Cham. https://doi.org/10.1007/978-3-031-42505-9_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-42505-9_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42504-2
Online ISBN: 978-3-031-42505-9
eBook Packages: Computer ScienceComputer Science (R0)