mlsanityData to 14 Oct 2026

On the causality-preservation capabilities of generative modelling

arXiv 2301.01109 ↗First posted 3 Jan 2023cs.LG econ.EMcited by 1

Not on the map. Why?

Abstract (arXiv)

Modeling lies at the core of both the financial and the insurance industry for a wide variety of tasks. The rise and development of machine learning and deep learning models have created many opportunities to improve our modeling toolbox. Breakthroughs in these fields often come with the requirement of large amounts of data. Such large datasets are often not publicly available in finance and insurance, mainly due to privacy and ethics concerns. This lack of data is currently one of the main hurdles in developing better models. One possible option to alleviating this issue is generative modeling. Generative models are capable of simulating fake but realistic-looking data, also referred to as synthetic data, that can be shared more freely. Generative Adversarial Networks (GANs) is such a model that increases our capacity to fit very high-dimensional distributions of data. While research on GANs is an active topic in fields like computer vision, they have found limited adoption within the human sciences, like economics and insurance. Reason for this is that in these fields, most questions are inherently about identification of causal effects, while to this day neural networks, which are at the center of the GAN framework, focus mostly on high-dimensional correlations. In this paper we study the causal preservation capabilities of GANs and whether the produced synthetic data can reliably be used to answer causal questions. This is done by performing causal analyses on the synthetic data, produced by a GAN, with increasingly more lenient assumptions. We consider the cross-sectional case, the time series case and the case with a complete structural model. It is shown that in the simple cross-sectional scenario where correlation equals causation the GAN preserves causality, but that challenges arise for more advanced analyses.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 78 references that are in the map. First posted on arXiv 3 Jan 2023.

Builds on

39 of 78 references.

References · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2019Invariant Risk Minimizationcited by 1,854
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  10. 2017Counterfactual Fairnesscited by 804
  11. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  12. 2019Modeling Tabular data using Conditional GANcited by 699
27 more
  1. 2018Recognition in Terra Incognitacited by 658
  2. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  3. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  4. 2020The Creation and Detection of Deepfakes: A Surveycited by 247
  5. 2018Differentially Private Generative Adversarial Networkcited by 235
  6. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  7. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  8. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  9. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  10. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  11. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  12. 2016Learning in Implicit Generative Modelscited by 125
  13. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  14. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 108
  15. 2018Synthesizing Tabular Data using Generative Adversarial Networkscited by 92
  16. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  17. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  18. 2019Detecting Overfitting of Deep Generative Networks via Latent Recoverycited by 44
  19. 2019PPGAN: Privacy-preserving Generative Adversarial Networkcited by 34
  20. 2022When do GANs replicate? On the choice of dataset sizecited by 34
  21. 2018Fairness GANcited by 32
  22. 2019Using Wasserstein Generative Adversarial Networks for the Design of Monte Carlo Simulationscited by 32
  23. 2017Context-Aware Generative Adversarial Privacycited by 27
  24. 2022On the Privacy Properties of GAN-generated Samplescited by 17
  25. 2021Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networkscited by 12
  26. 2020Synthetic Data Generation for Economistscited by 3
  27. 2021UnfairGAN: An Enhanced Generative Adversarial Network for Raindrop Removal from A Single Imagecited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Causal-Aware Tabular GANs with Reinforcement Learningcited by 1