# Structured Evaluation of Synthetic Tabular Data

arXiv: https://arxiv.org/abs/2403.10424 · HTML: https://mlsanity.com/paper/2403.10424/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [Why do tree-based models still outperform deep learning on tabular data?](https://mlsanity.com/paper/2207.08815/) (2022)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning](https://mlsanity.com/paper/2008.09202/) (2020)
- [VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data](https://mlsanity.com/paper/2006.11941/) (2020)
- [TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data](https://mlsanity.com/paper/2207.05295/) (2022)
- [CrossCat: A Fully Bayesian Nonparametric Method for Analyzing Heterogeneous, High Dimensional Data](https://mlsanity.com/paper/1512.01272/) (2015)
- [MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regime](https://mlsanity.com/paper/2307.07997/) (2023)

## Built on by (most cited first, 7 of 7)

- [Struct-Bench: A Benchmark for Differentially Private Structured Text Generation](https://mlsanity.com/paper/2509.10696/) (2025)
- [Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models](https://mlsanity.com/paper/2607.21636/) (2026)
- [A Sobering Look at Tabular Data Generation via Probabilistic Circuits](https://mlsanity.com/paper/2603.23016/) (2026)
- [Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis](https://mlsanity.com/paper/2509.20768/) (2025)
- [Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI](https://mlsanity.com/paper/2510.04622/) (2025)
- [Generating High-quality Privacy-preserving Synthetic Data](https://mlsanity.com/paper/2602.06390/) (2026)
- [MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation](https://mlsanity.com/paper/2609.39628/) (2026)

## Abstract (arXiv)

Tabular data is common yet typically incomplete, small in volume, and access-restricted due to privacy concerns. Synthetic data generation offers potential solutions. Many metrics exist for evaluating the quality of synthetic tabular data; however, we lack an objective, coherent interpretation of the many metrics. To address this issue, we propose an evaluation framework with a single, mathematical objective that posits that the synthetic data should be drawn from the same distribution as the observed data. Through various structural decomposition of the objective, this framework allows us to reason for the first time the completeness of any set of metrics, as well as unifies existing metrics, including those that stem from fidelity considerations, downstream application, and model-based approaches. Moreover, the framework motivates model-free baselines and a new spectrum of metrics. We evaluate structurally informed synthesizers and synthesizers powered by deep learning. Using our structured framework, we show that synthetic data generators that explicitly represent tabular structure outperform other methods, especially on smaller datasets.