mlsanityData to 7 Oct 2026

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

arXiv 2006.11941 ↗First posted 21 Jun 2020cs.LG stat.MLcited by 66

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 11; 2023: 11; 2024: 14; 2025: 11; 2026: 13.

66 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  3. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  4. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 81
  5. 2023Generative Table Pre-training Empowers Models for Tabular Predictioncited by 55
  6. 2023Learning to Maximize Mutual Information for Dynamic Feature Selectioncited by 54
  7. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 38
  8. 2022Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimizationcited by 32
  9. 2021Identifiable Generative Models for Missing Not at Random Data Imputationcited by 30
  10. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  11. 2025A Closer Look at Multimodal Representation Collapsecited by 25
  12. 2023Estimating Conditional Mutual Information for Dynamic Feature Selectioncited by 20
38 more
  1. 2022Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlocited by 19
  2. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 17
  3. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 16
  4. 2021Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluationcited by 15
  5. 2024An improved tabular data generator with VAE-GMM integrationcited by 13
  6. 2024Balanced Mixed-Type Tabular Data Synthesis with Diffusion Modelscited by 12
  7. 2024Generative AI and Process Systems Engineering: The Next Frontiercited by 8
  8. 2024Structured Evaluation of Synthetic Tabular Datacited by 7
  9. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 7
  10. 2022Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformationcited by 5
  11. 2023Variational Mixture of HyperGenerators for Learning Distributions Over Functionscited by 5
  12. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  13. 2024Data Augmentation with Variational Autoencoder for Imbalanced Datasetcited by 5
  14. 2021Medical data wrangling with sequential variational autoencoderscited by 4
  15. 2022GEDI: A Graph-based End-to-end Data Imputation Frameworkcited by 4
  16. 2023Predictive World Models from Real-World Partial Observationscited by 4
  17. 2023MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regimecited by 4
  18. 2023Generalized Oversampling for Learning from Imbalanced datasets and Associated Theorycited by 4
  19. 2024P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Modelscited by 4
  20. 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Featurescited by 4
  21. 2021Causally Constrained Data Synthesis for Private Data Releasecited by 3
  22. 2021Bi-Discriminator Class-Conditional Tabular GANcited by 3
  23. 2022Generative Modeling of Complex Datacited by 3
  24. 2022Leveraging variational autoencoders for multiple data imputationcited by 3
  25. 2023Differentially Private Synthetic Data Generation via Lipschitz-Regularised Variational Autoencoderscited by 3
  26. 2023Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learningcited by 3
  27. 2024Tree-Regularized Tabular Embeddingscited by 3
  28. 2022A Variational Autoencoder for Heterogeneous Temporal and Longitudinal Datacited by 2
  29. 2022Discovery and density estimation of latent confounders in Bayesian networks with evidence lower boundcited by 2
  30. 2024Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasetscited by 2
  31. 2024A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approachescited by 2
  32. 2025Evaluating Generative Models for Tabular Data: Novel Metrics and Benchmarkingcited by 2
  33. 2025Incomplete Data, Complete Dynamics: A Diffusion Approachcited by 2
  34. 2022GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studiescited by 1
  35. 2024Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarioscited by 1
  36. 2025A Generalized Theory of Mixup for Structure-Preserving Synthetic Datacited by 1
  37. 2025LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Modelscited by 1
  38. 2025IVGAE: Handling Incomplete Heterogeneous Data with a Variational Graph Autoencodercited by 1

50 most cited of 66 All 66 (JSON)