# Selection, Ignorability and Challenges With Causal Fairness

arXiv: https://arxiv.org/abs/2202.13774 · HTML: https://mlsanity.com/paper/2202.13774/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [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)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [The Use and Misuse of Counterfactuals in Ethical Machine Learning](https://mlsanity.com/paper/2102.05085/) (2021)
- [Causal Reasoning for Algorithmic Fairness](https://mlsanity.com/paper/1805.05859/) (2018)
- [Strong Completeness and Faithfulness in Bayesian Networks](https://mlsanity.com/paper/1302.4973/) (2013)
- [The Sensitivity of Counterfactual Fairness to Unmeasured Confounding](https://mlsanity.com/paper/1907.01040/) (2019)
- [A Causal Bayesian Networks Viewpoint on Fairness](https://mlsanity.com/paper/1907.06430/) (2019)
- [Separable Effects for Causal Inference in the Presence of Competing Events](https://mlsanity.com/paper/1901.09472/) (2019)

## Built on by (most cited first, 16 of 16)

- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Counterfactual Fairness with Partially Known Causal Graph](https://mlsanity.com/paper/2205.13972/) (2022)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Learning Counterfactually Invariant Predictors](https://mlsanity.com/paper/2207.09768/) (2022)
- [Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework](https://mlsanity.com/paper/2311.18460/) (2023)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)
- [Navigating Fairness Measures and Trade-Offs](https://mlsanity.com/paper/2307.08484/) (2023)
- [What is Fair? Defining Fairness in Machine Learning for Health](https://mlsanity.com/paper/2406.09307/) (2024)
- [Results on Counterfactual Invariance](https://mlsanity.com/paper/2307.08519/) (2023)
- [Consistent End-to-End Estimation for Counterfactual Fairness](https://mlsanity.com/paper/2310.17687/) (2023)
- [Counterfactual Fairness Is Not Demographic Parity, and Other Observations](https://mlsanity.com/paper/2402.02663/) (2024)
- [A Review of Fairness and A Practical Guide to Selecting Context-Appropriate Fairness Metrics in Machine Learning](https://mlsanity.com/paper/2411.06624/) (2024)
- [AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis](https://mlsanity.com/paper/2504.19621/) (2025)
- [On the Need and Applicability of Causality for Fairness: A Unified Framework for AI Auditing and Legal Analysis](https://mlsanity.com/paper/2207.04053/) (2022)
- [Unfair Utilities and First Steps Towards Improving Them](https://mlsanity.com/paper/2306.00636/) (2023)
- [Causal Transfer in Medical Image Analysis](https://mlsanity.com/paper/2603.24388/) (2026)

## Abstract (arXiv)

In this paper we look at popular fairness methods that use causal counterfactuals. These methods capture the intuitive notion that a prediction is fair if it coincides with the prediction that would have been made if someone's race, gender or religion were counterfactually different. In order to achieve this, we must have causal models that are able to capture what someone would be like if we were to counterfactually change these traits. However, we argue that any model that can do this must lie outside the particularly well behaved class that is commonly considered in the fairness literature. This is because in fairness settings, models in this class entail a particularly strong causal assumption, normally only seen in a randomised controlled trial. We argue that in general this is unlikely to hold. Furthermore, we show in many cases it can be explicitly rejected due to the fact that samples are selected from a wider population. We show this creates difficulties for counterfactual fairness as well as for the application of more general causal fairness methods.