Abstract
Microarray data has the characteristics of high dimension and few samples, which brings much difficulty to its processing. It is necessary to expand microarray data to increase the data sample size. Although the traditional generative adversarial network (GAN) could expand the sample of microarray data set, it could not get the corresponding label value of the generated sample and may generate “dirty” samples. Although the conditional generative adversarial network could get the labels of the generated samples, it is difficult to make the algorithm converge, and there are also “dirty” samples in the generated samples. To ensure that the algorithm could converge and the generated samples have corresponding labels and eliminate the “dirty” samples in the generated samples, an improved conditional generative adversarial network based on feature matching penalty and probability model setting threshold is proposed. On one hand, to improve the convergence probability of the CGAN, a feature matching penalty strategy is proposed in this study, which consists in finding a Nash equilibrium to a two-player non-cooperative game. On the other hand, to overcome the problem of the “dirty” samples from the generated samples, a strategy of the probability model is proposed to set the threshold, which could screen high-quality samples and discard “dirty” samples. The proposed CGAN could improve the classification accuracy as well as data generation ability, which is conducive to the diagnosis of diseases and the development of functional genomics. Experimental results on several public microarray data sets verifies the effectiveness of the proposed CGAN.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Huang, D.S.: Study on Mining Method of Microarray Data, 1st edn. Science press, Beijing (2009)
Diederik, P.K., Max, W.: Auto-encoding variational bayes. CoRR, abs/1312.6114 (2013)
Dou, Z.Y., Zhou, Z.H. Huang, S.J.: Unsupervised bilingual lexicon induction via latent variable models. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 621–626 (2018)
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. arXiv preprint arXiv:1511.05644 (2015)
Goodfellow, I., et al.: Generative adversarial nets. In: Conference and Workshop on Neural Information Processing Systems (2014)
Denton, E., Chintala, S., Szlam, A., Fergus, R.: Deep generative image models using a laplacian pyramid of adversarial networks. arXiv preprint arXiv:1506.05751 (2015)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Im, D.J., Kim, C.D., Jiang, H., Memisevic, R.: Generating images with recurrent adversarial networks. arXiv preprint arXiv:1602.05110 (2016)
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Info-Gan: inter-pretable representation learning by information maximizing generative adversarial nets. arXiv preprint arXiv:1606.03657 (2016)
Zhao, J.B., Mathieu, M., LeCun, Y.: Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126 (2016)
Hamid, E., Werner, Z., Gerhard, W.: Mixture density generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5520–5829(2019)
Li, S.Q., Liu, Y.: Remote sensing sample generation method based on generative adversarial network. In: Bulletin of Surveying and Mapping (2019)
Hoang, T., Truyen, T., Svetha, V.: Improving generalization and stability of generative adversarial networks. In: International Conference on Learning Representations (2019)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Huang, S.W., Lin, C. T., Chen, S. P., Wu, Y.Y., Lai, S.H.: AugGAN: cross domain adaptation with GAN-based data augmentation. In: European Conference on Computer Vision (2018)
Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. arXiv preprint arXiv:1606.03498 (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)
Zhu, Z., Ong,Y.S., Dash, M.: Markov blanket-embedded genetic algorithm for gene selection. Pattern Recogn. 49(11), 3236–3248 (2007)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Brodley, C.E., Utgoff, P.E.: Multivariate decision trees. Mach. Learn. 19(1), 45–77 (1995)
Zhou, Z.H.: Machine Learning, 1st edn. Tsinghua University Press, Beijing (2016)
Acknowledgments
This work was supported by the National Natural Science Foundation of China [Nos. 61976108 and 61572241], the National Key R&D Program of China [No. 2017YFC0806600].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, S., Han, F., Liang, WY., Jiang, J. (2020). An Improved Conditional Generative Adversarial Network for Microarray Data. In: Huang, DS., Bevilacqua, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2020. Lecture Notes in Computer Science(), vol 12463. Springer, Cham. https://doi.org/10.1007/978-3-030-60799-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-60799-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60798-2
Online ISBN: 978-3-030-60799-9
eBook Packages: Computer ScienceComputer Science (R0)