Learning conditional variational autoencoders with missing covariates

Conditional variational autoencoders (CVAEs) are versatile deep latent variable models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes that the data samples are independent, whereas more recent conditional VAE models, such as the Gaussian process (GP) prior VAEs, can account for complex correlation structures across all data samples. While several methods have been proposed to learn standard VAEs from partially observed datasets, these methods fall short for conditional VAEs. In this work, we propose a method to learn conditional VAEs from datasets in which auxiliary covariates can contain missing values as well. The proposed method augments the conditional VAEs with a prior distribution for the missing covariates and estimates their posterior using amortised variational inference. At training time, our method accounts for the uncertainty associated with the missing covariates while simultaneously maximising the evidence lower bound. We develop computationally efficient methods to learn CVAEs and GP prior VAEs that are compatible with mini-batching. Our experiments on simulated datasets as well as on real-world biomedical datasets show that the proposed method outperforms previous methods in learning conditional VAEs from non-temporal, temporal, and longitudinal datasets.

DOI

10.1016/j.patcog.2023.110113

Citation

Ramchandran, S, Tikhonov, G, Lönnroth, O, Tiikkainen, P & Lähdesmäki, H 2024, ' Learning conditional variational autoencoders with missing covariates ', Pattern Recognition, vol. 147, 110113 . https://doi.org/10.1016/j.patcog.2023.110113

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202312117130

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata

Learning conditional variational autoencoders with missing covariates

Access rights

URL

Journal Title

Journal ISSN

Volume Title

Authors

Date

Department

Major/Subject

Mcode

Degree programme

Language

Pages

Series

Abstract

Description

Keywords

Other note

DOI

Citation

Permanent link to this item

Collections