On Disentanglement in Gaussian Process Variational Autoencoders

Abstract

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.

References in corpus (9)

• Auto-Encoding Variational Bayes
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Recent Advances in Autoencoder-Based Representation Learning
• Understanding disentangling in $\beta$-VAE
• Weakly-Supervised Disentanglement Without Compromises
• Disentangled Sequential Autoencoder
• Disentangling Factors of Variation Using Few Labels
• A Survey of Inductive Biases for Factorial Representation-Learning
• Scalable Gaussian Process Variational Autoencoders

Cited by in corpus (2)

• MGP-AttTCN: An Interpretable Machine Learning Model for the Prediction of Sepsis
• Algorithm Fairness in AI for Medicine and Healthcare