# Fairness-Accuracy Trade-Offs: A Causal Perspective

arXiv: https://arxiv.org/abs/2405.15443 · HTML: https://mlsanity.com/paper/2405.15443/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [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)
- [Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination](https://mlsanity.com/paper/1408.6491/) (2014)
- [Lagrangian Duality for Constrained Deep Learning](https://mlsanity.com/paper/2001.09394/) (2020)
- [A Confidence-Based Approach for Balancing Fairness and Accuracy](https://mlsanity.com/paper/1601.05764/) (2016)
- [PC-Fairness: A Unified Framework for Measuring Causality-based Fairness](https://mlsanity.com/paper/1910.12586/) (2019)
- [Partial Counterfactual Identification from Observational and Experimental Data](https://mlsanity.com/paper/2110.05690/) (2021)
- [Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy](https://mlsanity.com/paper/2012.02972/) (2020)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [Fair Data Adaptation with Quantile Preservation](https://mlsanity.com/paper/1911.06685/) (2019)
- [Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree](https://mlsanity.com/paper/2305.13938/) (2023)
- [Causal Fairness for Outcome Control](https://mlsanity.com/paper/2306.05066/) (2023)
- [Reconciling Predictive and Statistical Parity: A Causal Approach](https://mlsanity.com/paper/2306.05059/) (2023)

## Built on by (most cited first, 10 of 10)

- [Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems](https://mlsanity.com/paper/2505.18139/) (2025)
- [Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspective](https://mlsanity.com/paper/2501.14710/) (2025)
- [Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models](https://mlsanity.com/paper/2502.21123/) (2025)
- [FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA](https://mlsanity.com/paper/2510.19421/) (2025)
- [Causal Graph Neural Networks for Healthcare](https://mlsanity.com/paper/2511.02531/) (2025)
- [A pipeline for enabling path-specific causal fairness in observational health data](https://mlsanity.com/paper/2601.09841/) (2026)
- [Evaluating Causal Discovery Algorithms for Path-Specific Fairness and Utility in Healthcare](https://mlsanity.com/paper/2603.15926/) (2026)
- [Choosing a parallel heterogeneous ensemble method for tabular classification](https://mlsanity.com/paper/2607.05103/) (2026)
- [GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness Audits](https://mlsanity.com/paper/2608.02877/) (2026)
- [Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization](https://mlsanity.com/paper/2608.22820/) (2026)

## Abstract (arXiv)

Systems based on machine learning may exhibit discriminatory behavior based on sensitive characteristics such as gender, sex, religion, or race. In light of this, various notions of fairness and methods to quantify discrimination were proposed, leading to the development of numerous approaches for constructing fair predictors. At the same time, imposing fairness constraints may decrease the utility of the decision-maker, highlighting a tension between fairness and utility. This tension is also recognized in legal frameworks, for instance in the disparate impact doctrine of Title VII of the Civil Rights Act of 1964 -- in which specific attention is given to considerations of business necessity -- possibly allowing the usage of proxy variables associated with the sensitive attribute in case a high-enough utility cannot be achieved without them. In this work, we analyze the tension between fairness and accuracy from a causal lens for the first time. We introduce the notion of a path-specific excess loss (PSEL) that captures how much the predictor's loss increases when a causal fairness constraint is enforced. We then show that the total excess loss (TEL), defined as the difference between the loss of predictor fair along all causal pathways vs. an unconstrained predictor, can be decomposed into a sum of more local PSELs. At the same time, enforcing a causal constraint often reduces the disparity between demographic groups. Thus, we introduce a quantity that summarizes the fairness-utility trade-off, called the causal fairness/utility ratio, defined as the ratio of the reduction in discrimination vs. the excess loss from constraining a causal pathway. This quantity is suitable for comparing the fairness-utility trade-off across causal pathways. Finally, as our approach requires causally-constrained fair predictors, we introduce a new neural approach for causally-constrained fair learning.