Abstract
Learning from incomplete data has been recognized as one of the fundamental challenges in deep learning. There are many more or less complicated methods for processing missing data by neural networks in the literature. In this paper, we show that flow-based generative models can work directly on images with missing data to produce full images without missing parts. We name this behavior Missing Glow Phenomenon. We present experiments that document such behaviors and propose theoretical justification of such phenomena.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Batista, G.E., Monard, M.C., et al.: A study of k-nearest neighbour as an imputation method. In: HIS, vol. 87, pp. 251–260 (2002)
Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.: Neural ordinary differential equations. arXiv preprint arXiv:1806.07366 (2018)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B (Methodol.) 39(1), 1–22 (1977)
Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press (2016)
Goodfellow, I.J., et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)
Gupta, M., et al.: Monotonic calibrated interpolated look-up tables. J. Mach. Learn. Res. 17(1), 3790–3836 (2016)
Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1 \(\times \) 1 convolutions. arXiv preprint arXiv:1807.03039 (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
Li, S.C.X., Marlin, B.: Learning from irregularly-sampled time series: a missing data perspective. In: International Conference on Machine Learning, pp. 5937–5946. PMLR (2020)
Little, R.J., Rubin, D.B.: Statistical Analysis with Missing Data, vol. 793. Wiley, Hoboken (2019)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015)
Mattei, P.A., Frellsen, J.: MIWAE: deep generative modelling and imputation of incomplete data sets. In: International Conference on Machine Learning, pp. 4413–4423. PMLR (2019)
McKnight, P.E., McKnight, K.M., Sidani, S., Figueredo, A.J.: Missing Data: A Gentle Introduction. Guilford Press (2007)
Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530–1538. PMLR (2015)
Richardson, T.W., Wu, W., Lin, L., Xu, B., Bernal, E.A.: MCFlow: Monte Carlo flow models for data imputation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14205–14214 (2020)
Rubin, D.B.: Inference and missing data. Biometrika 63(3), 581–592 (1976)
Sharpe, P.K., Solly, R.: Dealing with missing values in neural network-based diagnostic systems. Neural Comput. Appl. 3(2), 73–77 (1995)
Śmieja, M., Struski, Ł, Tabor, J., Marzec, M.: Generalized RBF kernel for incomplete data. Knowl. Based Syst. 173, 150–162 (2019)
Smieja, M., Struski, Ł., Tabor, J., Zieliński, B., Spurek, P.: Processing of missing data by neural networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 2724–2734 (2018)
Sovilj, D., et al.: Extreme learning machine for missing data using multiple imputations. Neurocomputing 174, 220–231 (2016)
Xie, J., Xu, L., Chen, E.: Image denoising and inpainting with deep neural networks. Adv. Neural. Inf. Process. Syst. 25, 341–349 (2012)
Yeh, R.A., Chen, C., Yian Lim, T., Schwing, A.G., Hasegawa-Johnson, M., Do, M.N.: Semantic image inpainting with deep generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5485–5493 (2017)
Yoon, J., Jordon, J., Schaar, M.: GAIN: missing data imputation using generative adversarial nets. In: International Conference on Machine Learning, pp. 5689–5698. PMLR (2018)
Zhang, Y., Zheng, Z., Hu, R.: Super resolution using segmentation-prior self-attention generative adversarial network. arXiv preprint arXiv:2003.03489 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sendera, M., Struski, Ł., Spurek, P. (2021). Missing Glow Phenomenon: Learning Disentangled Representation of Missing Data. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)