Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data

Abstract

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and noise of input sources. In this work, we propose the variational selective autoencoder (VSAE), a general framework to learn representations from partially-observed heterogeneous data. VSAE learns the latent dependencies in heterogeneous data by modeling the joint distribution of observed data, unobserved data, and the imputation mask which represents how the data are missing. It results in a unified model for various downstream tasks including data generation and imputation. Evaluation on both low-dimensional and high-dimensional heterogeneous datasets for these two tasks shows improvement over state-of-the-art models.

arXiv commentInternational Conference on Artificial Intelligence and Statistics (AISTATS) 2021

References in corpus (8)

• Auto-Encoding Variational Bayes
• MissForest - nonparametric missing value imputation for mixed-type data
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Multimodal Machine Learning: A Survey and Taxonomy
• Joint Multimodal Learning with Deep Generative Models
• MisGAN: Learning from Incomplete Data with Generative Adversarial Networks
• EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
• Data Generation as Sequential Decision Making

Cited by in corpus (2)

• Deep Generative Imputation Model for Missing Not At Random Data
• Learning Multimodal VAEs through Mutual Supervision