mlsanityData to 7 Oct 2026

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

arXiv 2202.04599 ↗First posted 9 Feb 2022cs.LG stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

Variational Autoencoders (VAEs) have recently been highly successful at imputing and acquiring heterogeneous missing data. However, within this specific application domain, existing VAE methods are restricted by using only one layer of latent variables and strictly Gaussian posterior approximations. To address these limitations, we present HH-VAEM, a Hierarchical VAE model for mixed-type incomplete data that uses Hamiltonian Monte Carlo with automatic hyper-parameter tuning for improved approximate inference. Our experiments show that HH-VAEM outperforms existing baselines in the tasks of missing data imputation and supervised learning with missing features. Finally, we also present a sampling-based approach for efficiently computing the information gain when missing features are to be acquired with HH-VAEM. Our experiments show that this sampling-based approach is superior to alternatives based on Gaussian approximations.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 9 Feb 2022.

Builds on

30 of 63 references.

References · 30

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2019An Introduction to Variational Autoencoderscited by 997
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  6. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  7. 2018Conditional Neural Processescited by 421
  8. 2016Ladder Variational Autoencoderscited by 315
  9. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  10. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  11. 2017Advances in Variational Inferencecited by 236
  12. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 207
18 more
  1. 2018Handling Incomplete Heterogeneous Data using VAEscited by 148
  2. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  3. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  4. 2019Preventing Posterior Collapse with delta-VAEscited by 86
  5. 2018EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEcited by 85
  6. 2020VAEM: a Deep Generative Model for Heterogeneous Mixed Type Datacited by 66
  7. 2013Hamiltonian Monte Carlo for Hierarchical Modelscited by 50
  8. 2018Hamiltonian Variational Auto-Encodercited by 41
  9. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36
  10. 2018Processing of missing data by neural networkscited by 36
  11. 2021Monte Carlo Variational Auto-Encoderscited by 36
  12. 2020VAEs in the Presence of Missing Datacited by 30
  13. 2020Capturing Label Characteristics in VAEscited by 30
  14. 2020Sliced Kernelized Stein Discrepancycited by 23
  15. 2019Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Datacited by 16
  16. 2018Active Feature Acquisition with Supervised Matrix Completioncited by 11
  17. 2021Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Datacited by 10
  18. 2021Medical data wrangling with sequential variational autoencoderscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 6; 2025: 5; 2026: 3.

19 papers.

Sort:

By area:

  1. 2023Transformed Distribution Matching for Missing Value Imputationcited by 31
  2. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 17
  3. 2025Stochastic Encodings for Active Feature Acquisitioncited by 8
  4. 2023Variational Mixture of HyperGenerators for Learning Distributions Over Functionscited by 5
  5. 2024Optimal Transport for Structure Learning Under Missing Datacited by 5
  6. 2023Predictive World Models from Real-World Partial Observationscited by 4
  7. 2024Knockout: A simple way to handle missing inputscited by 4
  8. 2025Cohort-Based Active Modality Acquisitioncited by 4
  9. 2025Tractable Representation Learning with Probabilistic Circuitscited by 4
  10. 2025Learning-To-Measure: In-Context Active Feature Acquisitioncited by 4
  11. 2024In-Database Data Imputationcited by 3
  12. 2022Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent spacecited by 2
7 more
  1. 2024A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approachescited by 2
  2. 2026Missingness-aware Data Imputation via AI-powered Bayesian Generative Modelingcited by 2
  3. 2024mDAE : modified Denoising AutoEncoder for missing data imputationcited by 1
  4. 2023Learning variational autoencoders via MCMC speed measurescited by 0
  5. 2025Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantificationcited by 0
  6. 2026Order-Agnostic Autoregressive Modelling with Missing Datacited by 0
  7. 2026Latent Diffusion for Missing Datacited by 0