# Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder

arXiv: https://arxiv.org/abs/2011.11878 · HTML: https://mlsanity.com/paper/2011.11878/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 30 of 45)

- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Learning Fair Representation via Distributional Contrastive Disentanglement](https://mlsanity.com/paper/2206.08743/) (2022)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries](https://mlsanity.com/paper/2110.14690/) (2021)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [Modeling Techniques for Machine Learning Fairness: A Survey](https://mlsanity.com/paper/2111.03015/) (2021)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Meta-Causal Feature Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.10156/) (2022)
- [Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model](https://mlsanity.com/paper/2306.01424/) (2023)
- [Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies](https://mlsanity.com/paper/2203.09672/) (2022)
- [Learning for Counterfactual Fairness from Observational Data](https://mlsanity.com/paper/2307.08232/) (2023)
- [Counterfactual Generative Modeling with Variational Causal Inference](https://mlsanity.com/paper/2410.12730/) (2024)
- [CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement](https://mlsanity.com/paper/2503.07938/) (2025)
- [A Survey of Deep Causal Models and Their Industrial Applications](https://mlsanity.com/paper/2209.08860/) (2022)
- [Counterfactually Fair Representation](https://mlsanity.com/paper/2311.05420/) (2023)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [Counterfactual Fairness by Combining Factual and Counterfactual Predictions](https://mlsanity.com/paper/2409.01977/) (2024)
- [Disentangled Representation with Causal Constraints for Counterfactual Fairness](https://mlsanity.com/paper/2208.09147/) (2022)
- [Travel Demand Forecasting: A Fair AI Approach](https://mlsanity.com/paper/2303.01692/) (2023)
- [SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems](https://mlsanity.com/paper/2307.15786/) (2023)
- [Causality from Bottom to Top: A Survey](https://mlsanity.com/paper/2403.11219/) (2024)
- [LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching](https://mlsanity.com/paper/2510.14623/) (2025)
- [Consistent End-to-End Estimation for Counterfactual Fairness](https://mlsanity.com/paper/2310.17687/) (2023)
- [Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness](https://mlsanity.com/paper/2106.08161/) (2021)
- [CMVAE: Causal Meta VAE for Unsupervised Meta-Learning](https://mlsanity.com/paper/2302.09731/) (2023)
- [Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement](https://mlsanity.com/paper/2406.00987/) (2024)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [Contagion Effect Estimation Using Proximal Embeddings](https://mlsanity.com/paper/2306.02479/) (2023)

## Abstract (arXiv)

The problem of fair classification can be mollified if we develop a method to remove the embedded sensitive information from the classification features. This line of separating the sensitive information is developed through the causal inference, and the causal inference enables the counterfactual generations to contrast the what-if case of the opposite sensitive attribute. Along with this separation with the causality, a frequent assumption in the deep latent causal model defines a single latent variable to absorb the entire exogenous uncertainty of the causal graph. However, we claim that such structure cannot distinguish the 1) information caused by the intervention (i.e., sensitive variable) and 2) information correlated with the intervention from the data. Therefore, this paper proposes Disentangled Causal Effect Variational Autoencoder (DCEVAE) to resolve this limitation by disentangling the exogenous uncertainty into two latent variables: either 1) independent to interventions or 2) correlated to interventions without causality. Particularly, our disentangling approach preserves the latent variable correlated to interventions in generating counterfactual examples. We show that our method estimates the total effect and the counterfactual effect without a complete causal graph. By adding a fairness regularization, DCEVAE generates a counterfactual fair dataset while losing less original information. Also, DCEVAE generates natural counterfactual images by only flipping sensitive information. Additionally, we theoretically show the differences in the covariance structures of DCEVAE and prior works from the perspective of the latent disentanglement.