Abstract
Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an efficient technique for this task, exploiting a recent framework we proposed for missing data imputation called graph imputation neural network (GINN). The key idea is to leverage both supervised and unsupervised data to build a graph of similarities between points in the dataset. Then, we augment the dataset by severely damaging a few of the nodes (up to 80% of their features), and reconstructing them using a variation of GINN. On several benchmark datasets, we show that our method can obtain significant improvements compared to a fully-supervised model, and we are able to augment the datasets up to a factor of \(10\times \). This points to the power of graph-based neural networks to represent structural affinities in the samples for tasks of data reconstruction and augmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceeding of the 34th International Conference on Machine Learning (ICML), vol. 70, pp. 214–223 (2017)
Battaglia, P.W., Hamrick, J.B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., Faulkner, R., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)
Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7(Nov), 2399–2434 (2006)
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.: Mixmatch: a holistic approach to semi-supervised learning. arXiv preprint arXiv:1905.02249 (2019)
Chapelle, O., Schlkopf, B., Zien, A.: Semi-Supervised Learning, 1st edn. The MIT Press (2010)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)
Cui, X., Goel, V., Kingsbury, B.: Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans. Audio Speech Lang. Process. 23(9), 1469–1477 (2015)
Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems, pp. 529–536 (2005)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Proceeding of the 3rd International Conference for Learning Representations (ICLR) (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the 2017 International Conference on Learning Representations (ICLR) (2017)
Lee, D.H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML. vol. 3, p. 2 (2013)
Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546–3554 (2015)
Spinelli, I., Scardapane, S., Uncini, A.: Missing Data Imputation with Adversarially-trained Graph Convolutional Networks. arXiv preprint arXiv:1905.01907 (2019)
Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised Data Augmentation. arXiv preprint arXiv:1904.12848 (Apr 2019)
Yoon, J., Jordon, J., van der Schaar, M.: Gain: Missing data imputation using generative adversarial nets. In: Proceedings of the 35th International Conference of Machine Learning (ICML), pp. 1–10 (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Spinelli, I., Scardapane, S., Scarpiniti, M., Uncini, A. (2021). Efficient Data Augmentation Using Graph Imputation Neural Networks. In: Esposito, A., Faundez-Zanuy, M., Morabito, F., Pasero, E. (eds) Progresses in Artificial Intelligence and Neural Systems. Smart Innovation, Systems and Technologies, vol 184. Springer, Singapore. https://doi.org/10.1007/978-981-15-5093-5_6
Download citation
DOI: https://doi.org/10.1007/978-981-15-5093-5_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5092-8
Online ISBN: 978-981-15-5093-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)