Abstract
Generative adversarial networks (GAN)-based approaches have been extensively investigated whereas GAN-inspired regression (i.e., numeric prediction) has rarely been studied in image and video processing domains. The lack of sufficient labeled data in many real-world cases poses great challenges to regression methods, which generally require sufficient labeled samples for their training. In this regard, we propose a unified framework that combines a robust autoencoder and a generative convolutional neural network (GCNN)-based regression model to address the regression problem. Our model is able to generate high-quality artificial samples via augmenting the size of a small number of training samples for better training effects. Extensive experiments are conducted on two real-world datasets and the results show that our proposed model consistently outperforms a set of advanced techniques under various evaluation metrics.
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
Similar content being viewed by others
References
Ning, X., et al.: Rating prediction via generative convolutional neural networks based regression. Pattern Recognit. Lett. (2018)
Andreas, C., Steinwart, I.: Consistency and robustness of kernel-based regression in convex risk minimization. Bernoulli 13(3), 799–819 (2007)
Hu, H., Qi, G.-J.: state-frequency memory recurrent neural networks. In: ICML (2017)
Suk, H.I., Lee, S.W., Shen, D.: Deep ensemble learning of sparse regression models for brain disease diagnosis. Med. Image Anal. 37, 101–113 (2017)
Ning, X., Yao, L., Wang, X., Benatallah, B.: Calling for response: automatically distinguishing situation-aware tweets during crises. In: Cong, G., Peng, W.-C., Zhang, W.E., Li, C., Sun, A. (eds.) ADMA 2017. LNCS (LNAI), vol. 10604, pp. 195–208. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-69179-4_14
Liu, M.-Y., Tuzel, O.: Coupled generative adversarial networks. In: Advances in Neural Information Processing Systems (2016)
Chong, Z., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
Eliashberg, J., Hui, S.K., John, Z.J.: Assessing box office performance using movie scripts: a kernel-based approach. TKDE 26(11), 2639–2648 (2014)
Gerber, M.S.: Predicting crime using Twitter and kernel density estimation. Decis. Support Syst. 61, 115–125 (2014)
Huang, S., et al.: Regression-based hypergraph learning for image clustering and classification. arXiv preprint arXiv:1603.04150 (2016)
Zhang, L., Aggarwal, C., Qi, G.-J.: Stock price prediction via discovering multi-frequency trading patterns. In: Proceedings of the 23rd ACM SIGKDD (2017)
Montero, J.-M., Mínguez, R., Fernández-Avilés, G.: Housing price prediction: parametric versus semi-parametric spatial hedonic models. J. Geogr. Syst. 20(1), 27–55 (2018)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Ning, X., Yao, L., Wang, X., Benatallah, B., Zhang, S., Zhang, X. (2018). Data-Augmented Regression with Generative Convolutional Network. In: Hacid, H., Cellary, W., Wang, H., Paik, HY., Zhou, R. (eds) Web Information Systems Engineering – WISE 2018. WISE 2018. Lecture Notes in Computer Science(), vol 11234. Springer, Cham. https://doi.org/10.1007/978-3-030-02925-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-02925-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02924-1
Online ISBN: 978-3-030-02925-8
eBook Packages: Computer ScienceComputer Science (R0)