TY - GEN
T1 - Semi-Supervised learning with normalizing flows
AU - Izmailov, Pavel
AU - Kirichenko, Polina
AU - Finzi, Marc
AU - Wilson, Andrew Gordon
N1 - Funding Information:
This research is supported by an Amazon Research Award, Facebook Research, Amazon Machine Learning Research Award, NSF I-DISRE 193471, NIH R01 DA048764-01A1, NSF IIS-1910266, and NSF 1922658 NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science.
Publisher Copyright:
© International Conference on Machine Learning, ICML 2020. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood. We propose FlowGMM, an end-to-end approach to generative semi-supervised learning with normalizing flows, using a latent Gaussian mixture model. FlowGMM is distinct in its simplicity, unified treatment of labeled and unlabeled data with an exact likelihood, interpretability, and broad applicability beyond image data. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data, tabular data, and semi-supervised image classification. We also show that FlowGMM can discover interpretable structure, provide real-time optimization-free feature visualizations, and specify well calibrated predictive distributions.
AB - Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood. We propose FlowGMM, an end-to-end approach to generative semi-supervised learning with normalizing flows, using a latent Gaussian mixture model. FlowGMM is distinct in its simplicity, unified treatment of labeled and unlabeled data with an exact likelihood, interpretability, and broad applicability beyond image data. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data, tabular data, and semi-supervised image classification. We also show that FlowGMM can discover interpretable structure, provide real-time optimization-free feature visualizations, and specify well calibrated predictive distributions.
UR - http://www.scopus.com/inward/record.url?scp=85105252039&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105252039&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85105252039
T3 - 37th International Conference on Machine Learning, ICML 2020
SP - 4565
EP - 4580
BT - 37th International Conference on Machine Learning, ICML 2020
A2 - Daume, Hal
A2 - Singh, Aarti
PB - International Machine Learning Society (IMLS)
T2 - 37th International Conference on Machine Learning, ICML 2020
Y2 - 13 July 2020 through 18 July 2020
ER -