Log In Sign Up

On Disentanglement in Gaussian Process Variational Autoencoders

by   Simon Bing, et al.

Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we are observing. While many models have been introduced to learn such disentangled representations, only few attempt to explicitly exploit the structure of sequential data. We investigate the disentanglement properties of Gaussian process variational autoencoders, a class of models recently introduced that have been successful in different tasks on time series data. Our model exploits the temporal structure of the data by modeling each latent channel with a GP prior and employing a structured variational distribution that can capture dependencies in time. We demonstrate the competitiveness of our approach against state-of-the-art unsupervised and weakly-supervised disentanglement methods on a benchmark task. Moreover, we provide evidence that we can learn meaningful disentangled representations on real-world medical time series data.


Multivariate Time Series Imputation with Variational Autoencoders

Multivariate time series with missing values are common in many areas, f...

Dimension Reduction for time series with Variational AutoEncoders

In this work, we explore dimensionality reduction techniques for univari...

Markovian Gaussian Process Variational Autoencoders

Deep generative models are widely used for modelling high-dimensional ti...

Gaussian Process Prior Variational Autoencoders

Variational autoencoders (VAE) are a powerful and widely-used class of m...

Probabilistic structure discovery in time series data

Existing methods for structure discovery in time series data construct i...

Learning Disentangled Representations of Satellite Image Time Series

In this paper, we investigate how to learn a suitable representation of ...

Learning Disentangled Representations for Time Series

Time-series representation learning is a fundamental task for time-serie...