Variational Selective Autoencoder

Yu Gong, Hossein Hajimirsadeghi, Jiawei He, Megha Nawhal, Thibaut Durand, Greg Mori
Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, PMLR 118:1-17, 2020.

Abstract

Despite promising progress on unimodal data imputation (e.g. image inpainting), models for multimodal data imputation are far from satisfactory. In this work, we propose variational selective autoencoder (VSAE) for this task. Learning only from partially-observed data, VSAE can model the joint distribution of observed/unobserved modalities and the imputation mask, resulting in a unied model for various down-stream tasks including data generation and imputation. Evaluation on synthetic high-dimensional and challenging low-dimensional multimodal datasets shows improvement over the state-of-the-art imputation models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v118-gong20a, title = {Variational Selective Autoencoder}, author = {Gong, Yu and Hajimirsadeghi, Hossein and He, Jiawei and Nawhal, Megha and Durand, Thibaut and Mori, Greg}, booktitle = {Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference}, pages = {1--17}, year = {2020}, editor = {Zhang, Cheng and Ruiz, Francisco and Bui, Thang and Dieng, Adji Bousso and Liang, Dawen}, volume = {118}, series = {Proceedings of Machine Learning Research}, month = {08 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v118/gong20a/gong20a.pdf}, url = {https://proceedings.mlr.press/v118/gong20a.html}, abstract = { Despite promising progress on unimodal data imputation (e.g. image inpainting), models for multimodal data imputation are far from satisfactory. In this work, we propose variational selective autoencoder (VSAE) for this task. Learning only from partially-observed data, VSAE can model the joint distribution of observed/unobserved modalities and the imputation mask, resulting in a unied model for various down-stream tasks including data generation and imputation. Evaluation on synthetic high-dimensional and challenging low-dimensional multimodal datasets shows improvement over the state-of-the-art imputation models. } }
Endnote
%0 Conference Paper %T Variational Selective Autoencoder %A Yu Gong %A Hossein Hajimirsadeghi %A Jiawei He %A Megha Nawhal %A Thibaut Durand %A Greg Mori %B Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference %C Proceedings of Machine Learning Research %D 2020 %E Cheng Zhang %E Francisco Ruiz %E Thang Bui %E Adji Bousso Dieng %E Dawen Liang %F pmlr-v118-gong20a %I PMLR %P 1--17 %U https://proceedings.mlr.press/v118/gong20a.html %V 118 %X Despite promising progress on unimodal data imputation (e.g. image inpainting), models for multimodal data imputation are far from satisfactory. In this work, we propose variational selective autoencoder (VSAE) for this task. Learning only from partially-observed data, VSAE can model the joint distribution of observed/unobserved modalities and the imputation mask, resulting in a unied model for various down-stream tasks including data generation and imputation. Evaluation on synthetic high-dimensional and challenging low-dimensional multimodal datasets shows improvement over the state-of-the-art imputation models.
APA
Gong, Y., Hajimirsadeghi, H., He, J., Nawhal, M., Durand, T. & Mori, G.. (2020). Variational Selective Autoencoder. Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, in Proceedings of Machine Learning Research 118:1-17 Available from https://proceedings.mlr.press/v118/gong20a.html.

Related Material