Longitudinal Variational Autoencoder

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2021

Major/Subject

Mcode

Degree programme

Language

en

Pages

11

Series

24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), Proceedings of Machine Learning Research ; Volume 130

Abstract

Longitudinal datasets measured repeatedly over time from individual subjects, arise in many biomedical, psychological, social, and other studies. A common approach to analyse high-dimensional data that contains missing values is to learn a low-dimensional representation using variational autoencoders (VAEs). However, standard VAEs assume that the learnt representations are i.i.d., and fail to capture the correlations between the data samples. We propose the Longitudinal VAE (L-VAE), that uses a multi-output additive Gaussian process (GP) prior to extend the VAE's capability to learn structured low-dimensional representations imposed by auxiliary covariate information, and derive a new KL divergence upper bound for such GPs. Our approach can simultaneously accommodate both time-varying shared and random effects, produce structured low-dimensional representations, disentangle effects of individual covariates or their interactions, and achieve highly accurate predictive performance. We compare our model against previous methods on synthetic as well as clinical datasets, and demonstrate the state-of-theart performance in data imputation, reconstruction, and long-term prediction tasks.

Description

Keywords

Other note

Citation

Ramchandran, S, Tikhonov, G, Kujanpaa, K, Koskinen, M & Lahdesmaki, H 2021, Longitudinal Variational Autoencoder . in A Banerjee & K Fukumizu (eds), 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS) . Proceedings of Machine Learning Research, vol. 130, Microtome Publishing, International Conference on Artificial Intelligence and Statistics, Virtual, Online, 13/04/2021 . < http://proceedings.mlr.press/v130/ramchandran21b.html >