Tabular Data Synthesis

Follow this topic Ask about this topic

Tabular data synthesis studies how to generate realistic rows of mixed numerical and categorical data for uses such as data sharing, augmentation, and clinical research. Common approaches include GANs such as CTGAN, variational autoencoders, diffusion models, language-model generators, and methods that encode causal or relational structure. Evaluation compares statistical and high-order fidelity, downstream utility on prediction tasks, and privacy risks such as membership inference, often across real-world datasets and controlled benchmarks. The central challenge is balancing fidelity, utility, and privacy: matching marginal distributions alone may miss important relationships or individual-level behavior, while stronger realism can increase leakage risk.

Latest papers

19 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Sequential versus fully conditional specification for tree-based synthesis of health data
Oct 26, 2026R{é}my Chapelle, Mohammed SedkiSynthetic Clinical Data Generation Tabular Data Synthesis
CB, CESP, EVDG · Université Paris-Saclay, UVSQ, Inserm, CESP, 94807, Villejuif, France · Université Paris-Saclay, Université Paris Cité, ENS Paris-Saclay, CNRS, SSA, Inserm, Centre Borelli, 91190, Gif-sur-Yvette, France +2
Faithful Federated Tabular Data Synthesis
Oct 24, 2026Zilong Cao, Hai Zhang, Xuan BiSynthetic Data Generation Synthetic Tabular Data Generation
School of Mathematics, Northwest University · Carlson School of Management, University of Minnesota
DiffLTM: Continuous Diffusions Large Tabular Models for Conditional Generation
Oct 21, 2026Alankrita Bhatt, Mukur Gupta, Andrea Montanari +1Tabular Diffusion Models Synthetic Tabular Data Generation
Granica Computing Inc. · Stanford University
Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure
Sep 7, 2026Alexander DoudkinUser Simulation Tabular Data Synthesis
Minds AI Labs, Inc.
Differentially Private Paired Table-Image Multimodal Synthesis
Sep 1, 2026Kai Chen, Josephine Lamp, Somesh Jha +1Synthetic Data Generation Cross-Modal Alignment
University of Virginia · Dexcom · University of Wisconsin-Madison
KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation
Aug 23, 2026Jalen Jiang, Chufan Gao, Ethan Rasmussen +2Synthetic Clinical Data Generation Synthetic Data Generation
Siebel School of Computing and Data Science University of Illinois Urbana-Champaign · Mayo Clinic Alix School of Medicine
PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization
Jun 16, 2026Arshia Ilaty, Hossein Shirazi, Manasi Chitale +5Synthetic Tabular Data Generation Tabular Data Synthesis
San Diego State University, San Diego, CA 92182 USA. · University of California, Irvine, CA 92697 USA.
LLM-as-a-Discriminator: When Synthetic Tables Still Look Real
Jun 1, 2026Manel Slokom, Malek Slokom, Thierno KantePrivacy Auditing Tabular Data Synthesis
Vrije Universiteit, Amsterdam · Equativ, Paris · EDICIA, Nantes
TabChange: Precise Attribute Changes in Tabular Data
May 30, 2026Arjun Dahal, Yu Lei, Raghu N. Kacker +1Adversarial Representation Learning Counterfactual Explanations
The University of Texas at Arlington · Arlington, Texas, USA · Information Technology Laboratory +2
Geometry-Aware Tabular Diffusion
May 23, 2026David Turtora ZagardoTabular Diffusion Models Tabular Data Synthesis
Independent Researcher.
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
May 12, 2026Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu +1Membership Inference Attacks Tabular Diffusion Models
University of Waterloo · Vector Institute
On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
May 7, 2026Masoumeh Shafieinejad, D. B. Emerson, Behnoosh Zamanlooy +5Data Leakage Membership Inference Attacks
Vector Institute · McMaster University · University of Toronto +1
Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion
May 7, 2026Eugenio Lomurno, Filippo Balzarini, Francesco Benelle +2Diffusion Model Guidance Inference-Time Optimization
Politecnico di Milano, AIRLab, Italy
Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning
May 6, 2026Xinyan Han, Yan Lu, Xiaoyu Lin +5Synthetic Data Augmentation Privacy-Preserving ML
1Tsinghua University · 2Southeast University · 3Siemens China
DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis
Apr 5, 2026Hristo Petkov, Calum MacLellan, Feng DongCausal Structure Learning Tabular Data Synthesis
Department of Computer and Information Sciences, University of Strathclyde, 16 Richmond Street, Glasgow, G1 1XQ, Lanarkshire, United Kingdom.
SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection
Mar 31, 2026Hochan Son, Xiaofeng Lin, Jason Ni +1Synthetic Data Selection Tabular Data Synthesis
Department of Statistics, University of California, Los Angeles · Department of Mathematics, University of California, Los Angeles
ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning
Mar 11, 2026Xiaofeng Lin, Seungbae Kim, Zhuoya Li +3Synthetic Tabular Data Generation Tabular Data Synthesis
University of California, Los Angeles, USA · University of South Florida, USA · Cisco, USA +1
Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis
Feb 25, 2026Bahrul Ilmi Nasution, Mark Elliot, Richard AllmendingerSynthetic Tabular Data Generation Tabular Data Synthesis
Department of Social Statistics, The University of Manchester, Oxford Rd, Manchester, M13 9PL, UK. · Alliance Manchester Business School, The University of Manchester, Booth Street West, Manchester, M15 6PB, UK.
Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework
Jun 12, 2024Zineb Senane, Axel Karlsson, Lele Cao +6Synthetic Benchmark Generation Causal Inference
KTH Royal Institute of Technology · Stockholm, Sweden · King AI Labs, Microsoft +2

Oct 26, 2026J/K move · Enter open · S save

Sequential versus fully conditional specification for tree-based synthesis of health data

R{é}my Chapelle, Mohammed Sedki

CB, CESP, EVDG · Université Paris-Saclay, UVSQ, Inserm, CESP, 94807, Villejuif, France · Université Paris-Saclay, Université Paris Cité, ENS Paris-Saclay, CNRS, SSA, Inserm, Centre Borelli, 91190, Gif-sur-Yvette, France+2

Synthetic Clinical Data Generation Tabular Data Synthesis Synthetic Data Evaluation Conditional Generative Modeling

Open paper AskPDF arXiv

Disseminating synthetic data in place of original ones is a promising way to enforce privacy while complying with open science principles, especially in the healthcare domain. To keep pace with the rate at which researchers collect such data, there is a need for fast and flexible synthesis procedures. A popular class of such procedures is based on models of conditional distributions induced by decision trees. Such models can be combined into a synthetic distribution following two main approaches: sequential specification and fully conditional specification. However, there is currently no recommendation on which specification to use to optimize the risk-utility tradeoffs. In this work, we use both specifications to synthesize medical datasets by combining tree-based models of conditional distributions. We compare the quality of the resulting synthetic data using several metrics of risk and utility. Our results indicate no general superiority of either specification over the other. Sequential synthesis seems sensitive to the ordering of the variables, while the fully conditional specification involves more hyperparameters and incurs higher computational costs, which may limit its suitability for off-the-shelf synthesis procedures.