Data to 14 Oct 2026

Causal Fairness Analysis

arXiv 2207.11385 ↗First posted 23 Jul 2022cs.AI cs.LG stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

Decision-making systems based on AI and machine learning have been used throughout a wide range of real-world scenarios, including healthcare, law enforcement, education, and finance. It is no longer far-fetched to envision a future where autonomous systems will be driving entire business decisions and, more broadly, supporting large-scale decision-making infrastructure to solve society's most challenging problems. Issues of unfairness and discrimination are pervasive when decisions are being made by humans, and remain (or are potentially amplified) when decisions are made using machines with little transparency, accountability, and fairness. In this paper, we introduce a framework for textitcausal fairness analysis with the intent of filling in this gap, i.e., understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms that generate the disparity in the first place, challenge we call the Fundamental Problem of Causal Fairness Analysis (FPCFA). In order to solve the FPCFA, we study the problem of decomposing variations and empirical measures of fairness that attribute such variations to structural mechanisms and different units of the population. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature. Finally, we study which causal assumptions are minimally needed for performing causal fairness analysis and propose a Fairness Cookbook, which allows data scientists to assess the existence of disparate impact and disparate treatment.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 4 of its 67 references that are in the map. First posted on arXiv 23 Jul 2022.

Builds on

4 of 67 references.

References · 4

2017On Fairness and Calibrationcited by 406
2018The Measure and Mismeasure of Fairnesscited by 95
2016On the (im)possibility of fairnesscited by 11
2017Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 16; 2024: 9; 2025: 12; 2026: 3.

43 papers.

Sort:

By area:

2023CLadder: Assessing Causal Reasoning in Language Modelscited by 107
2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
2023Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairnesscited by 17
2022Backtracking Counterfactualscited by 16
2023Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Modelcited by 14
2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
2022Applications of statistical causal inference in software engineeringcited by 12
2023No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imagingcited by 11
2025FairPFN: A Tabular Foundation Model for Causal Fairnesscited by 9
2023Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Differencecited by 8
2023Causal Fairness for Outcome Controlcited by 8
2024FairPFN: Transformers Can do Counterfactual Fairnesscited by 8

31 more

2024Counterfactual Fairness by Combining Factual and Counterfactual Predictionscited by 8
2024Rethinking Fair Representation Learning for Performance-Sensitive Taskscited by 8
2024The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learningcited by 8
2023Reconciling Predictive and Statistical Parity: A Causal Approachcited by 7
2023Rating Sentiment Analysis Systems for Bias through a Causal Lenscited by 6
2024Auditing Fairness under Unobserved Confoundingcited by 6
2023How Far Can Fairness Constraints Help Recover From Biased Data?cited by 5
2024Causality from Bottom to Top: A Surveycited by 5
2023Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledgecited by 4
2023Group-blind optimal transport to group parity and its constrained variantscited by 4
2023Consistent End-to-End Estimation for Counterfactual Fairnesscited by 4
2024A New Paradigm for Counterfactual Reasoning in Fairness and Recoursecited by 3
2024What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learningcited by 3
2024Test-Time Fairness and Robustness in Large Language Modelscited by 3
2023Fair Enough? A map of the current limitations of the requirements to have fair algorithmscited by 2
2025Modeling Discrimination with Causal Abstractioncited by 2
2025Estimating Probabilities of Causation with Machine Learning Modelscited by 2
2023Fair Clustering: A Causal Perspectivecited by 1
2025Learning Probabilities of Causation with Mask-Augmented Datacited by 1
2025A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generationcited by 1
2025FairTabGen: High-Fidelity and Fair Synthetic Health Data Generation from Limited Samplescited by 1
2022Causal foundations of bias, disparity and fairnesscited by 0
2023Re-formalization of Individual Fairnesscited by 0
2025Revisiting the Berkeley Admissions data: Statistical Tests for Causal Hypothesescited by 0
2025Testing for Causal Fairnesscited by 0
2025Causal Feature Learning in the Social Sciencescited by 0
2025DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlationcited by 0
2025From Black-box to Causal-box: Towards Building More Interpretable Modelscited by 0
2026Causal Bias Detection in Generative Artificial Intelligencecited by 0
2026Counterfactually Fair Regression via Optimal Transportcited by 0
2026Proxy reliance in large language model decisions is uncalibrated to predictive evidencecited by 0