mlsanityData to 14 Oct 2026

TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness

arXiv 2606.05361 ↗First posted 3 Jun 2026stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Missing data imputation in large-scale surveys faces two challenges that are not well handled by current tabular diffusion methods. First, structural skips, cells made inapplicable by questionnaire design, should not be imputed but are often conflated with item nonresponse. Second, ordinal responses encode ordered categories, yet most pipelines treat them as nominal levels through one-hot or analog-bit encodings. We introduce TabSODA (Tabular diffusion with Skip pattern detection and Ordinal Awareness), an Expectation-Maximization (EM)-based diffusion imputer built on the Elucidated Diffusion Model (EDM) framework. TabSODA propagates structural skips through the denoising loss and reverse-time sampler, and represents ordinal variables with cumulative-probit scalar latents while retaining analog-bit encodings for nominal variables. When a codebook skip mask is available, TabSODA uses it directly; otherwise, the TabSODA+SKIP variant estimates the mask from raw responses and questionnaire order using a CART-based skip-pattern miner. On Population Assessment of Tobacco and Health (PATH) study and the National Survey on Drug Use and Health (NSDUH), two nationally representative U.S. surveys, TabSODA reduces ordinal MACE by up to 23.7% and improves categorical accuracy by up to 9% over the strongest baseline across MCAR, MAR, and MNAR masking. The skip miner achieves near-perfect precision on both datasets, allowing TabSODA+SKIP to closely track the codebook-mask variant.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

18 of 41 references.

References · 18

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  4. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  5. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  6. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  7. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  8. 2018Handling Incomplete Heterogeneous Data using VAEscited by 149
  9. 2019Rank consistent ordinal regression for neural networks with application to age estimationcited by 133
  10. 2020Handling Missing Data with Graph Representation Learningcited by 133
  11. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  12. 2022Diffusion models for missing value imputation in tabular datacited by 77
6 more
  1. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 63
  2. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 39
  3. 2020MCFlow: Monte Carlo Flow Models for Data Imputationcited by 37
  4. 2023ReMasker: Imputing Tabular Data with Masked Autoencodingcited by 37
  5. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
  6. 2021Using the Softplus Function to Construct Alternative Link Functions in Generalized Linear Models and Beyondcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MissDDIM: Deterministic and Efficient Conditional Diffusion for Tabular Data Imputation
  2. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputation
  3. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model
  4. 2024Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flow
  5. 2025MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation
  6. 2026Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation
  7. 2025Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
  8. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generation