mlsanityData to 7 Oct 2026

Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilities

arXiv 2405.20959 ↗First posted 31 May 2024cs.AI cs.DBcited by 8

Not on the map. Why?

Abstract (arXiv)

In an era of rapidly advancing data-driven applications, there is a growing demand for data in both research and practice. Synthetic data have emerged as an alternative when no real data is available (e.g., due to privacy regulations). Synthesizing tabular data presents unique and complex challenges, especially handling (i) missing values, (ii) dataset imbalance, (iii) diverse column types, and (iv) complex data distributions, as well as preserving (i) column correlations, (ii) temporal dependencies, and (iii) integrity constraints (e.g., functional dependencies) present in the original dataset. While substantial progress has been made recently in the context of generational models, there is no one-size-fits-all solution for tabular data today, and choosing the right tool for a given task is therefore no trivial task. In this paper, we survey the state of the art in Tabular Data Synthesis (TDS), examine the needs of users by defining a set of functional and non-functional requirements, and compile the challenges associated with meeting those needs. In addition, we evaluate the reported performance of 36 popular research TDS tools about these requirements and develop a decision guide to help users find suitable TDS tools for their applications. The resulting decision guide also identifies significant research gaps.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 51 of its 136 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

51 of 136 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  8. 2019An Introduction to Variational Autoencoderscited by 997
  9. 2019Modeling Tabular data using Conditional GANcited by 695
  10. 2019Neural Spline Flowscited by 590
  11. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  12. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
38 more
  1. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  2. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  3. 2018Differentially Private Generative Adversarial Networkcited by 235
  4. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  5. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
  6. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  7. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
  8. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  9. 2016Discrete Variational Autoencoderscited by 124
  10. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 93
  11. 2018Synthesizing Tabular Data using Generative Adversarial Networkscited by 92
  12. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  13. 2022STaSy: Score-based Tabular data Synthesiscited by 85
  14. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  15. 2019Graphical-model based estimation and inference for differential privacycited by 73
  16. 2023Diffusion Models for Time Series Applications: A Surveycited by 72
  17. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  18. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 42
  19. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesiscited by 42
  20. 2019Hybrid Models with Deep and Invertible Featurescited by 41
  21. 2022TTS-GAN: A Transformer-based Time-Series Generative Adversarial Networkcited by 41
  22. 2017Oversampling for Imbalanced Learning Based on K-Means and SMOTEcited by 38
  23. 2021Copula Flows for Synthetic Data Generationcited by 35
  24. 2018Differentially Private Data Generative Modelscited by 33
  25. 2022SOS: Score-based Oversampling for Tabular Datacited by 29
  26. 2022TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Datacited by 27
  27. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizingcited by 24
  28. 2020Kamino: Constraint-Aware Differentially Private Data Synthesiscited by 23
  29. 2023Regular Time-series Generation using SGMcited by 23
  30. 2020Relational Data Synthesis using Generative Adversarial Networks: A Design Space Explorationcited by 21
  31. 2023Synthetic Data Applications in Financecited by 21
  32. 2017SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generationcited by 20
  33. 2023On the Usefulness of Synthetic Tabular Data Generationcited by 12
  34. 2023PrivLava: Synthesizing Relational Data with Foreign Keys under Differential Privacycited by 11
  35. 2021DTGAN: Differential Private Training for Tabular GANscited by 7
  36. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Datacited by 7
  37. 2018A Formal Framework For Probabilistic Unclean Databasescited by 4
  38. 2021Synthesizing Linked Data Under Cardinality and Integrity Constraintscited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 13
  2. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesiscited by 4
  3. 2025Dependency-aware synthetic tabular data generationcited by 2
  4. 2025Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QAcited by 1
  5. 2026Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusioncited by 1
  6. 2025Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forestscited by 0
  7. 2025Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesiscited by 0
  8. 2026SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selectioncited by 0