mlsanityData to 14 Oct 2026

TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data

arXiv 2207.05295 ↗First posted 12 Jul 2022cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Synthetic tabular data generation becomes crucial when real data is limited, expensive to collect, or simply cannot be used due to privacy concerns. However, producing good quality synthetic data is challenging. Several probabilistic, statistical, generative adversarial networks (GANs), and variational auto-encoder (VAEs) based approaches have been presented for synthetic tabular data generation. Once generated, evaluating the quality of the synthetic data is quite challenging. Some of the traditional metrics have been used in the literature but there is lack of a common, robust, and single metric. This makes it difficult to properly compare the effectiveness of different synthetic tabular data generation methods. In this paper we propose a new universal metric, TabSynDex, for robust evaluation of synthetic data. The proposed metric assesses the similarity of synthetic data with real data through different component scores which evaluate the characteristics that are desirable for ``high quality'' synthetic data. Being a single score metric and having an implicit bound, TabSynDex can also be used to observe and evaluate the training of neural network based approaches. This would help in obtaining insights that was not possible earlier. We present several baseline models for comparative analysis of the proposed evaluation metric with existing generative models. We also give a comparative analysis between TabSynDex and existing synthetic tabular data evaluation metrics. This shows the effectiveness and universality of our metric over the existing metrics. Source Code: urlhttps://github.com/vikram2000b/tabsyndex

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 14 of its 49 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

14 of 49 references.

References · 14

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  4. 2019Modeling Tabular data using Conditional GANcited by 699
  5. 2016Adversarial Feature Learningcited by 350
  6. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  7. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  8. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  9. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  10. 2018Synthesizing Tabular Data using Generative Adversarial Networkscited by 92
  11. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  12. 2021TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networkscited by 34
2 more
  1. 2014Dirichlet Process Mixture Models for Modeling and Generating Synthetic Versions of Nested Categorical Datacited by 1
  2. 2016Bayesian mixture modeling for multivariate conditional distributionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 7; 2025: 12; 2026: 5.

27 papers.

Sort:

By area:

  1. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 41
  2. 2024Systematic Assessment of Tabular Data Synthesiscited by 18
  3. 2024Can I trust my fake data -- A comprehensive quality assessment framework for synthetic tabular data in healthcarecited by 17
  4. 2025A Survey on Efficient Large Language Model Training: From Data-centric Perspectivescited by 9
  5. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  6. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  7. 2024Structured Evaluation of Synthetic Tabular Datacited by 7
  8. 2025Struct-Bench: A Benchmark for Differentially Private Structured Text Generationcited by 7
  9. 2025Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Frameworkcited by 6
  10. 2024An evaluation framework for synthetic data generation modelscited by 5
  11. 2025Evaluating Differentially Private Generation of Domain-Specific Textcited by 5
  12. 2023MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regimecited by 4
15 more
  1. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  2. 2023Sharing is CAIRing: Characterizing Principles and Assessing Properties of Universal Privacy Evaluation for Synthetic Tabular Datacited by 2
  3. 2025Fairness Testing through Extreme Value Theorycited by 2
  4. 2022Evaluating Synthetic Tabular Data Generated To Augment Small Sample Datasetscited by 1
  5. 2025SHAP Distance: An Explainability-Aware Metric for Evaluating the Semantic Fidelity of Synthetic Tabular Datacited by 1
  6. 2024Permissioned Blockchain-based Framework for Ranking Synthetic Data Generatorscited by 0
  7. 2025Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraintscited by 0
  8. 2025GEM-T: Generative Tabular Data via Fitting Momentscited by 0
  9. 2025Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesiscited by 0
  10. 2025Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGencited by 0
  11. 2026Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Modelscited by 0
  12. 2026Evaluating quality in synthetic data generation for large tabular health datasetscited by 0
  13. 2026Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmarkcited by 0
  14. 2026PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimizationcited by 0
  15. 2026Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generationcited by 0