# The Sensitivity of Counterfactual Fairness to Unmeasured Confounding

arXiv: https://arxiv.org/abs/1907.01040 · HTML: https://mlsanity.com/paper/1907.01040/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 30 of 35)

- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Counterfactual harm](https://mlsanity.com/paper/2204.12993/) (2022)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [Stochastic Causal Programming for Bounding Treatment Effects](https://mlsanity.com/paper/2202.10806/) (2022)
- [A Neural Framework for Generalized Causal Sensitivity Analysis](https://mlsanity.com/paper/2311.16026/) (2023)
- [Selection, Ignorability and Challenges With Causal Fairness](https://mlsanity.com/paper/2202.13774/) (2022)
- [Counterfactual Fairness Is Basically Demographic Parity](https://mlsanity.com/paper/2208.03843/) (2022)
- [Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model](https://mlsanity.com/paper/2306.01424/) (2023)
- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [Treatment Effect Risk: Bounds and Inference](https://mlsanity.com/paper/2201.05893/) (2022)
- [Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders](https://mlsanity.com/paper/2210.05446/) (2022)
- [Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework](https://mlsanity.com/paper/2311.18460/) (2023)
- [Designing Long-term Group Fair Policies in Dynamical Systems](https://mlsanity.com/paper/2311.12447/) (2023)
- [Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference](https://mlsanity.com/paper/2302.11944/) (2023)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)
- [Mitigating Health Disparities in EHR via Deconfounder](https://mlsanity.com/paper/2210.15901/) (2022)
- [Are demographically invariant models and representations in medical imaging fair?](https://mlsanity.com/paper/2305.01397/) (2023)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Counterfactual Multi-Token Fairness in Text Classification](https://mlsanity.com/paper/2202.03792/) (2022)
- [The Equity Framework: Fairness Beyond Equalized Predictive Outcomes](https://mlsanity.com/paper/2205.01072/) (2022)
- [Counterfactual Generation Under Confounding](https://mlsanity.com/paper/2210.12368/) (2022)
- [Toward A Causal Framework for Modeling Perception](https://mlsanity.com/paper/2401.13408/) (2024)
- [Counterfactual Situation Testing: From Single to Multidimensional Discrimination](https://mlsanity.com/paper/2502.01267/) (2025)
- [On Counterfactual Data Augmentation Under Confounding](https://mlsanity.com/paper/2305.18183/) (2023)
- [Debiasing Alternative Data for Credit Underwriting Using Causal Inference](https://mlsanity.com/paper/2410.22382/) (2024)
- [Counterfactual Fairness with Graph Uncertainty](https://mlsanity.com/paper/2601.03203/) (2026)
- [Causal Inference on Networks under Misspecified Exposure Mappings: A Partial Identification Framework](https://mlsanity.com/paper/2602.03459/) (2026)
- [Counterfactual Fairness in Mortgage Lending via Matching and Randomization](https://mlsanity.com/paper/2112.02170/) (2021)
- [Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments](https://mlsanity.com/paper/2309.01780/) (2023)
- [Revisiting Technical Bias Mitigation Strategies](https://mlsanity.com/paper/2410.17433/) (2024)

## Abstract (arXiv)

Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In no small part, this has been due to the fact that causal models allow one to simultaneously leverage data and expert knowledge to remove discriminatory effects from predictions. However, one of the primary assumptions in causal modeling is that you know the causal graph. This introduces a new opportunity for bias, caused by misspecifying the causal model. One common way for misspecification to occur is via unmeasured confounding: the true causal effect between variables is partially described by unobserved quantities. In this work we design tools to assess the sensitivity of fairness measures to this confounding for the popular class of non-linear additive noise models (ANMs). Specifically, we give a procedure for computing the maximum difference between two counterfactually fair predictors, where one has become biased due to confounding. For the case of bivariate confounding our technique can be swiftly computed via a sequence of closed-form updates. For multivariate confounding we give an algorithm that can be efficiently solved via automatic differentiation. We demonstrate our new sensitivity analysis tools in real-world fairness scenarios to assess the bias arising from confounding.