# MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regime

arXiv: https://arxiv.org/abs/2307.07997 · HTML: https://mlsanity.com/paper/2307.07997/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 16 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Synthesizing Tabular Data using Generative Adversarial Networks](https://mlsanity.com/paper/1811.11264/) (2018)
- [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)
- [Airline Passenger Name Record Generation using Generative Adversarial Networks](https://mlsanity.com/paper/1807.06657/) (2018)
- [RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks](https://mlsanity.com/paper/1802.06403/) (2018)

## Built on by (most cited first, 4 of 4)

- [Structured Evaluation of Synthetic Tabular Data](https://mlsanity.com/paper/2403.10424/) (2024)
- [DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators](https://mlsanity.com/paper/2412.02467/) (2024)
- [Towards Biologically Plausible and Private Gene Expression Data Generation](https://mlsanity.com/paper/2402.04912/) (2024)
- [High-Quality Tabular Data Generation using Post-Selected VAE](https://mlsanity.com/paper/2407.13016/) (2024)

## Abstract (arXiv)

The potential of realistic and useful synthetic data is significant. However, current evaluation methods for synthetic tabular data generation predominantly focus on downstream task usefulness, often neglecting the importance of statistical properties. This oversight becomes particularly prominent in low sample scenarios, accompanied by a swift deterioration of these statistical measures. In this paper, we address this issue by conducting an evaluation of three state-of-the-art synthetic tabular data generators based on their marginal distribution, column-pair correlation, joint distribution and downstream task utility performance across high to low sample regimes. The popular CTGAN model shows strong utility, but underperforms in low sample settings in terms of utility. To overcome this limitation, we propose MargCTGAN that adds feature matching of de-correlated marginals, which results in a consistent improvement in downstream utility as well as statistical properties of the synthetic data.