# Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

arXiv: https://arxiv.org/abs/1610.08452 · HTML: https://mlsanity.com/paper/1610.08452/

## Key facts

- Cited by 369 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2016.

## Built on by (most cited first, 30 of 369)

- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://mlsanity.com/paper/2304.03738/) (2023)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [User-oriented Fairness in Recommendation](https://mlsanity.com/paper/2104.10671/) (2021)
- [Label-Imbalanced and Group-Sensitive Classification under Overparameterization](https://mlsanity.com/paper/2103.01550/) (2021)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Recent Advances in Optimal Transport for Machine Learning](https://mlsanity.com/paper/2306.16156/) (2023)
- [Fairness in Credit Scoring: Assessment, Implementation and Profit Implications](https://mlsanity.com/paper/2103.01907/) (2021)
- [Towards Fairness-Aware Federated Learning](https://mlsanity.com/paper/2111.01872/) (2021)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [DORO: Distributional and Outlier Robust Optimization](https://mlsanity.com/paper/2106.06142/) (2021)
- [Understanding and Mitigating Annotation Bias in Facial Expression Recognition](https://mlsanity.com/paper/2108.08504/) (2021)
- [AutoBalance: Optimized Loss Functions for Imbalanced Data](https://mlsanity.com/paper/2201.01212/) (2022)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness](https://mlsanity.com/paper/2202.08821/) (2022)
- [On Tilted Losses in Machine Learning: Theory and Applications](https://mlsanity.com/paper/2109.06141/) (2021)
- [Improving Fairness via Federated Learning](https://mlsanity.com/paper/2110.15545/) (2021)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Enforcing fairness in private federated learning via the modified method of differential multipliers](https://mlsanity.com/paper/2109.08604/) (2021)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)

## Abstract (arXiv)

Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the errors (or, misclassifications) over the given historical data. However, it is quite possible that the optimally trained classifier makes decisions for people belonging to different social groups with different misclassification rates (e.g., misclassification rates for females are higher than for males), thereby placing these groups at an unfair disadvantage. To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy.