mlsanityData to 14 Oct 2026

Handling Incomplete Heterogeneous Data using VAEs

arXiv 1807.03653 ↗First posted 10 Jul 2018cs.LG cs.AI stat.MLcited by 149

Not on the map. Why?

Abstract (arXiv)

Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not directly handle data that are heterogenous (mixed continuous and discrete) or incomplete (with missing data at random), which is indeed common in real-world applications. In this paper, we propose a general framework to design VAEs suitable for fitting incomplete heterogenous data. The proposed HI-VAE includes likelihood models for real-valued, positive real valued, interval, categorical, ordinal and count data, and allows accurate estimation (and potentially imputation) of missing data. Furthermore, HI-VAE presents competitive predictive performance in supervised tasks, outperforming supervised models when trained on incomplete data.

Key facts. Cited by 149 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 21; 2022: 33; 2023: 24; 2024: 24; 2025: 29; 2026: 18.

149 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  2. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  3. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  4. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 86
  5. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  6. 2022Diffusion models for missing value imputation in tabular datacited by 77
  7. 2023Learning to Maximize Mutual Information for Dynamic Feature Selectioncited by 56
  8. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 39
  9. 2023ReMasker: Imputing Tabular Data with Masked Autoencodingcited by 37
  10. 2023Large Language Models as Data Preprocessorscited by 34
  11. 2022Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimizationcited by 32
  12. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
38 more
  1. 2023Transformed Distribution Matching for Missing Value Imputationcited by 31
  2. 2021Identifiable Generative Models for Missing Not at Random Data Imputationcited by 30
  3. 2025A Closer Look at Multimodal Representation Collapsecited by 28
  4. 2021Spatial Aggregation and Temporal Convolution Networks for Real-time Krigingcited by 27
  5. 2021Ranking the information content of distance measurescited by 22
  6. 2023Estimating Conditional Mutual Information for Dynamic Feature Selectioncited by 21
  7. 2023Jellyfish: A Large Language Model for Data Preprocessingcited by 20
  8. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  9. 2022Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlocited by 19
  10. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
  11. 2021Learning Multimodal VAEs through Mutual Supervisioncited by 18
  12. 2022Maximizing information from chemical engineering data sets: Applications to machine learningcited by 17
  13. 2021Simultaneous Missing Value Imputation and Structure Learning with Groupscited by 16
  14. 2022Markovian Gaussian Process Variational Autoencoderscited by 16
  15. 2021Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluationcited by 15
  16. 2022Data Imputation with Iterative Graph Reconstructioncited by 15
  17. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  18. 2022Model-agnostic out-of-distribution detection using combined statistical testscited by 14
  19. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  20. 2021Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Datacited by 10
  21. 2022Learning Conditional Variational Autoencoders with Missing Covariatescited by 10
  22. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
  23. 2024Multimodal Data Integration for Precision Oncology: Challenges and Future Directionscited by 10
  24. 2022To Impute or not to Impute? Missing Data in Treatment Effect Estimationcited by 9
  25. 2024Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approachcited by 9
  26. 2021DAEMA: Denoising Autoencoder with Mask Attentioncited by 8
  27. 2023Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Datacited by 8
  28. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  29. 2022Sharing pattern submodels for prediction with missing valuescited by 7
  30. 2022EGG-GAE: scalable graph neural networks for tabular data imputationcited by 7
  31. 2023Continuous-time Autoencoders for Regular and Irregular Time Series Imputationcited by 6
  32. 2024Optimal Transport for Structure Learning Under Missing Datacited by 6
  33. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Modelcited by 6
  34. 2022Differentiable and Scalable Generative Adversarial Models for Data Imputationcited by 5
  35. 2022Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecturecited by 5
  36. 2022Gaussian Processes for Missing Value Imputationcited by 5
  37. 2022GEDI: A Graph-based End-to-end Data Imputation Frameworkcited by 5
  38. 2023Synthetic data generation for a longitudinal cohort study -- Evaluation, method extension and reproduction of published data analysis resultscited by 5

50 most cited of 149 All 149 (JSON)