# De-Biasing Generative Models using Counterfactual Methods

arXiv: https://arxiv.org/abs/2207.01575 · HTML: https://mlsanity.com/paper/2207.01575/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Causal Discovery with Reinforcement Learning](https://mlsanity.com/paper/1906.04477/) (2019)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Masked Gradient-Based Causal Structure Learning](https://mlsanity.com/paper/1910.08527/) (2019)
- [CausalVAE: Structured Causal Disentanglement in Variational Autoencoder](https://mlsanity.com/paper/2004.08697/) (2020)

## Built on by (most cited first, 3 of 3)

- [Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing](https://mlsanity.com/paper/2502.09564/) (2025)
- [Causal Structural Hypothesis Testing and Data Generation Models](https://mlsanity.com/paper/2210.11275/) (2022)
- [Towards Composable Distributions of Latent Space Augmentations](https://mlsanity.com/paper/2303.03462/) (2023)

## Abstract (arXiv)

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing generative models take causality into account. We propose a new decoder based framework named the Causal Counterfactual Generative Model (CCGM), which includes a partially trainable causal layer in which a part of a causal model can be learned without significantly impacting reconstruction fidelity. By learning the causal relationships between image semantic labels or tabular variables, we can analyze biases, intervene on the generative model, and simulate new scenarios. Furthermore, by modifying the causal structure, we can generate samples outside the domain of the original training data and use such counterfactual models to de-bias datasets. Thus, datasets with known biases can still be used to train the causal generative model and learn the causal relationships, but we can produce de-biased datasets on the generative side. Our proposed method combines a causal latent space VAE model with specific modification to emphasize causal fidelity, enabling finer control over the causal layer and the ability to learn a robust intervention framework. We explore how better disentanglement of causal learning and encoding/decoding generates higher causal intervention quality. We also compare our model against similar research to demonstrate the need for explicit generative de-biasing beyond interventions. Our initial experiments show that our model can generate images and tabular data with high fidelity to the causal framework and accommodate explicit de-biasing to ignore undesired relationships in the causal data compared to the baseline.