mlsanityData to 7 Oct 2026

TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data

arXiv 2501.12012 ↗First posted 21 Jan 2025cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Synthetic data generation for tabular datasets must balance fidelity, efficiency, and versatility to meet the demands of real-world applications. We introduce the Tabular Auto-Regressive Generative Network (TabularARGN), a flexible framework designed to handle mixed-type, multivariate, and sequential datasets. By training on all possible conditional probabilities, TabularARGN supports advanced features such as fairness-aware generation, imputation, and conditional generation on any subset of columns. The framework achieves state-of-the-art synthetic data quality while significantly reducing training and inference times, making it ideal for large-scale datasets with diverse structures. Evaluated across established benchmarks, including realistic datasets with complex relationships, TabularARGN demonstrates its capability to synthesize high-quality data efficiently. By unifying flexibility and performance, this framework paves the way for practical synthetic data generation across industries.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

33 of 59 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  5. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  6. 2019Modeling Tabular data using Conditional GANcited by 695
  7. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  8. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  9. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  10. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 273
  11. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  12. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
21 more
  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
  2. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  3. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
  4. 2016Neural Autoregressive Distribution Estimationcited by 94
  5. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 93
  6. 2022STaSy: Score-based Tabular data Synthesiscited by 85
  7. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
  8. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  9. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  10. 2022Training and Inference on Any-Order Autoregressive Models the Right Waycited by 64
  11. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 60
  12. 2021Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applicationscited by 47
  13. 2023TabMT: Generating tabular data with masked transformerscited by 36
  14. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  15. 2022Row Conditional-TGAN for generating synthetic relational databasescited by 15
  16. 2023DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generationcited by 13
  17. 2024Understanding and Mitigating Memorization in Diffusion Models for Tabular Datacited by 7
  18. 2023Strong statistical parity through fair synthetic datacited by 6
  19. 2024SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformerscited by 5
  20. 2024Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Datacited by 4
  21. 2021Composable Generative Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 5.

13 papers.

Sort:

By area:

  1. 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Featurescited by 4
  2. 2025RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Modelscited by 3
  3. 2025TABFAIRGDT: A Fast Fair Tabular Data Generator using Autoregressive Decision Treescited by 2
  4. 2026Improving TabPFN's Synthetic Data Generation by Integrating Causal Structurecited by 2
  5. 2025Improving Predictions on Highly Unbalanced Data Using Open Source Synthetic Data Upsamplingcited by 1
  6. 2025Democratizing Tabular Data Access with an Openunicodex2013Source Syntheticunicodex2013Data SDKcited by 1
  7. 2025A Note on Statistically Accurate Tabular Data Generation Using Large Language Modelscited by 0
  8. 2025Disjoint Generation of Synthetic Datacited by 0
  9. 2025GEM-T: Generative Tabular Data via Fitting Momentscited by 0
  10. 2025"AGI" team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTacited by 0
  11. 2026Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Datacited by 0
  12. 2026Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Datacited by 0
1 more
  1. 2026Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Datacited by 0