# Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?

arXiv: https://arxiv.org/abs/1912.01094 · HTML: https://mlsanity.com/paper/1912.01094/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2019.

## Built on by (most cited first, 30 of 50)

- [Multi-group Agnostic PAC Learnability](https://mlsanity.com/paper/2105.09989/) (2021)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)
- [Fair Classification with Adversarial Perturbations](https://mlsanity.com/paper/2106.05964/) (2021)
- [An Algorithmic Framework for Bias Bounties](https://mlsanity.com/paper/2201.10408/) (2022)
- [A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models](https://mlsanity.com/paper/2106.12887/) (2021)
- [Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions](https://mlsanity.com/paper/2301.11781/) (2023)
- [Fairness-Aware PAC Learning from Corrupted Data](https://mlsanity.com/paper/2102.06004/) (2021)
- [Removing biased data to improve fairness and accuracy](https://mlsanity.com/paper/2102.03054/) (2021)
- [A study on the distribution of social biases in self-supervised learning visual models](https://mlsanity.com/paper/2203.01854/) (2022)
- [Domain Adaptation meets Individual Fairness. And they get along](https://mlsanity.com/paper/2205.00504/) (2022)
- [A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms](https://mlsanity.com/paper/2204.10233/) (2022)
- [Bias Propagation in Federated Learning](https://mlsanity.com/paper/2309.02160/) (2023)
- [Robust Fairness-aware Learning Under Sample Selection Bias](https://mlsanity.com/paper/2105.11570/) (2021)
- [On Fair Selection in the Presence of Implicit and Differential Variance](https://mlsanity.com/paper/2112.05630/) (2021)
- [Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing](https://mlsanity.com/paper/2104.01634/) (2021)
- [How Costly is Noise? Data and Disparities in Consumer Credit](https://mlsanity.com/paper/2105.07554/) (2021)
- [Costs and Benefits of Fair Regression](https://mlsanity.com/paper/2106.08812/) (2021)
- [Consistent Range Approximation for Fair Predictive Modeling](https://mlsanity.com/paper/2212.10839/) (2022)
- [Can Information Flows Suggest Targets for Interventions in Neural Circuits?](https://mlsanity.com/paper/2111.05299/) (2021)
- [Metrizing Fairness](https://mlsanity.com/paper/2205.15049/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Adaptive Data Debiasing through Bounded Exploration](https://mlsanity.com/paper/2110.13054/) (2021)
- [Selection in the Presence of Implicit Bias: The Advantage of Intersectional Constraints](https://mlsanity.com/paper/2202.01661/) (2022)
- [Social Bias Meets Data Bias: The Impacts of Labeling and Measurement Errors on Fairness Criteria](https://mlsanity.com/paper/2206.00137/) (2022)
- [Algorithmic Censoring in Dynamic Learning Systems](https://mlsanity.com/paper/2305.09035/) (2023)
- [How Far Can Fairness Constraints Help Recover From Biased Data?](https://mlsanity.com/paper/2312.10396/) (2023)
- [Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspective](https://mlsanity.com/paper/2501.14710/) (2025)
- [Normalise for Fairness: A Simple Normalisation Technique for Fairness in Regression Machine Learning Problems](https://mlsanity.com/paper/2202.00993/) (2022)
- [Fairness in Forecasting of Observations of Linear Dynamical Systems](https://mlsanity.com/paper/2209.05274/) (2022)
- [A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier](https://mlsanity.com/paper/2310.12785/) (2023)

## Abstract (arXiv)

Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data may be biased, including having a more noisy or negatively biased labeling process on members of a disadvantaged group, or a decreased prevalence of positive or negative examples from the disadvantaged group, or both. Given such biased training data, Empirical Risk Minimization (ERM) may produce a classifier that not only is biased but also has suboptimal accuracy on the true data distribution. We examine the ability of fairness-constrained ERM to correct this problem. In particular, we find that the Equal Opportunity fairness constraint (Hardt, Price, and Srebro 2016) combined with ERM will provably recover the Bayes Optimal Classifier under a range of bias models. We also consider other recovery methods including reweighting the training data, Equalized Odds, and Demographic Parity. These theoretical results provide additional motivation for considering fairness interventions even if an actor cares primarily about accuracy.