VAEs in the Presence of Missing Data

by   Mark Collier, et al.

Real world datasets often contain entries with missing elements e.g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests. Variational Autoencoders (VAEs) are popular generative models often used for unsupervised learning. Despite their widespread use it is unclear how best to apply VAEs to datasets with missing data. We develop a novel latent variable model of a corruption process which generates missing data, and derive a corresponding tractable evidence lower bound (ELBO). Our model is straightforward to implement, can handle both missing completely at random (MCAR) and missing not at random (MNAR) data, scales to high dimensional inputs and gives both the VAE encoder and decoder principled access to indicator variables for whether a data element is missing or not. On the MNIST and SVHN datasets we demonstrate improved marginal log-likelihood of observed data and better missing data imputation, compared to existing approaches.


page 3

page 8

page 9


Autoencoders and Probabilistic Inference with Missing Data: An Exact Solution for The Factor Analysis Case

Latent variable models can be used to probabilistically "fill-in" missin...

Medical data wrangling with sequential variational autoencoders

Medical data sets are usually corrupted by noise and missing data. These...

Missing Value Imputation Based on Deep Generative Models

Missing values widely exist in many real-world datasets, which hinders t...

A Probabilistic Model of Cardiac Physiology and Electrocardiograms

An electrocardiogram (EKG) is a common, non-invasive test that measures ...

Missing Data Estimation in High-Dimensional Datasets: A Swarm Intelligence-Deep Neural Network Approach

In this paper, we examine the problem of missing data in high-dimensiona...

Disentangled VAE Representations for Multi-Aspect and Missing Data

Many problems in machine learning and related application areas are fund...

A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

This paper takes a step towards temporal reasoning in a dynamically chan...