VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

Abstract

Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and features of the same type having different marginal distributions. We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. VAEM is a deep generative model that is trained in a two stage manner such that the first stage provides a more uniform representation of the data to the second stage, thereby sidestepping the problems caused by heterogeneous data. We provide extensions of VAEM to handle partially observed data, and demonstrate its performance in data generation, missing data prediction and sequential feature selection tasks. Our results show that VAEM broadens the range of real-world applications where deep generative models can be successfully deployed. 1

Grafik Top
Authors
  • Ma, Chao
  • Tschiatschek, Sebastian
  • Turner, Richard E
  • Hernandez-Lobato, Jose Miguel
  • Zhang, Cheng
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS)
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Event Location
Virtual
Event Type
Conference
Event Dates
06.-12.12.2020
Series Name
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
Date
2020
Export
Grafik Top