# Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models

arXiv: https://arxiv.org/abs/2502.12796 · HTML: https://mlsanity.com/paper/2502.12796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [Causality for Machine Learning](https://mlsanity.com/paper/1911.10500/) (2019)
- [Universal Approximation with Deep Narrow Networks](https://mlsanity.com/paper/1905.08539/) (2019)
- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Causal Machine Learning for Healthcare and Precision Medicine](https://mlsanity.com/paper/2205.11402/) (2022)
- [Neural Causal Models for Counterfactual Identification and Estimation](https://mlsanity.com/paper/2210.00035/) (2022)
- [Counterfactual Identifiability of Bijective Causal Models](https://mlsanity.com/paper/2302.02228/) (2023)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [Wasserstein Generative Learning of Conditional Distribution](https://mlsanity.com/paper/2112.10039/) (2021)
- [Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries](https://mlsanity.com/paper/2302.00860/) (2023)
- [Identifiable Latent Polynomial Causal Models Through the Lens of Change](https://mlsanity.com/paper/2310.15580/) (2023)
- [Neural Causal Abstractions](https://mlsanity.com/paper/2401.02602/) (2024)
- [Counterfactual Fairness with Partially Known Causal Graph](https://mlsanity.com/paper/2205.13972/) (2022)
- [Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness](https://mlsanity.com/paper/2310.19691/) (2023)
- [Adversarial Learning for Counterfactual Fairness](https://mlsanity.com/paper/2008.13122/) (2020)
- [Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model](https://mlsanity.com/paper/2306.01424/) (2023)
- [Learning for Counterfactual Fairness from Observational Data](https://mlsanity.com/paper/2307.08232/) (2023)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges](https://mlsanity.com/paper/2405.05025/) (2024)
- [Counterfactual Fairness by Combining Factual and Counterfactual Predictions](https://mlsanity.com/paper/2409.01977/) (2024)
- [An Optimal Transport Approach to Estimating Causal Effects via Nonlinear Difference-in-Differences](https://mlsanity.com/paper/2108.05858/) (2021)
- [Consistent Optimal Transport with Empirical Conditional Measures](https://mlsanity.com/paper/2305.15901/) (2023)

## Abstract (arXiv)

One of the main concerns while deploying machine learning models in real-world applications is fairness. Counterfactual fairness has emerged as an intuitive and natural definition of fairness. However, existing methodologies for enforcing counterfactual fairness seem to have two limitations: (i) generating counterfactual samples faithful to the underlying causal graph, and (ii) as we argue in this paper, existing regularizers are mere proxies and do not directly enforce the exact definition of counterfactual fairness. In this work, our aim is to mitigate both issues. Firstly, we propose employing Neural Causal Models (NCMs) for generating the counterfactual samples. For implementing the abduction step in NCMs, the posteriors of the exogenous variables need to be estimated given a counterfactual query, as they are not readily available. As a consequence, L3 consistency with respect to the underlying causal graph cannot be guaranteed in practice due to the estimation errors involved. To mitigate this issue, we propose a novel kernel least squares loss term that enforces the L3 constraints explicitly. Thus, we obtain an improved counterfactual generation suitable for the counterfactual fairness task. Secondly, we propose a new MMD-based regularizer term that explicitly enforces the counterfactual fairness conditions into the base model while training. We show an improved trade-off between counterfactual fairness and generalization over existing baselines on synthetic and benchmark datasets.