# Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2104.10680 · HTML: https://mlsanity.com/paper/2104.10680/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records](https://mlsanity.com/paper/2001.09346/) (2020)
- [Generating Multi-Categorical Samples with Generative Adversarial Networks](https://mlsanity.com/paper/1807.01202/) (2018)
- [Kernel-based Approach to Handle Mixed Data for Inferring Causal Graphs](https://mlsanity.com/paper/1910.03055/) (2019)

## Built on by (most cited first, 12 of 12)

- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing](https://mlsanity.com/paper/2305.11602/) (2023)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation](https://mlsanity.com/paper/2302.11294/) (2023)
- [LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation](https://mlsanity.com/paper/2410.15828/) (2024)
- [CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data](https://mlsanity.com/paper/2503.04852/) (2025)
- [Causally Disentangled Generative Variational AutoEncoder](https://mlsanity.com/paper/2302.11737/) (2023)
- [CausalWrap: Model-Agnostic Causal Constraint Wrappers for Tabular Synthetic Data](https://mlsanity.com/paper/2603.02015/) (2026)
- [On the causality-preservation capabilities of generative modelling](https://mlsanity.com/paper/2301.01109/) (2023)
- [Joint Distributional Learning via Cramer-Wold Distance](https://mlsanity.com/paper/2310.16374/) (2023)
- [DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis](https://mlsanity.com/paper/2604.04290/) (2026)
- [Causal Parametric Drift Simulation: A Digital Twin Framework for Classifier Robustness Evaluation](https://mlsanity.com/paper/2605.09663/) (2026)

## Abstract (arXiv)

Synthetic data generation becomes prevalent as a solution to privacy leakage and data shortage. Generative models are designed to generate a realistic synthetic dataset, which can precisely express the data distribution for the real dataset. The generative adversarial networks (GAN), which gain great success in the computer vision fields, are doubtlessly used for synthetic data generation. Though there are prior works that have demonstrated great progress, most of them learn the correlations in the data distributions rather than the true processes in which the datasets are naturally generated. Correlation is not reliable for it is a statistical technique that only tells linear dependencies and is easily affected by the dataset's bias. Causality, which encodes all underlying factors of how the real data be naturally generated, is more reliable than correlation. In this work, we propose a causal model named Causal Tabular Generative Neural Network (Causal-TGAN) to generate synthetic tabular data using the tabular data's causal information. Extensive experiments on both simulated datasets and real datasets demonstrate the better performance of our method when given the true causal graph and a comparable performance when using the estimated causal graph.