# Unprocessing Seven Years of Algorithmic Fairness

arXiv: https://arxiv.org/abs/2306.07261 · HTML: https://mlsanity.com/paper/2306.07261/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [50 Years of Test (Un)fairness: Lessons for Machine Learning](https://mlsanity.com/paper/1811.10104/) (2018)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [Algorithmic Fairness Datasets: the Story so Far](https://mlsanity.com/paper/2202.01711/) (2022)
- [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020)
- [FairGBM: Gradient Boosting with Fairness Constraints](https://mlsanity.com/paper/2209.07850/) (2022)
- [ProPublica's COMPAS Data Revisited](https://mlsanity.com/paper/1906.04711/) (2019)
- [Group-Aware Threshold Adaptation for Fair Classification](https://mlsanity.com/paper/2111.04271/) (2021)
- [Promoting Fairness through Hyperparameter Optimization](https://mlsanity.com/paper/2103.12715/) (2021)
- [Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML](https://mlsanity.com/paper/2303.08485/) (2023)
- [Fairness Improves Learning from Noisily Labeled Long-Tailed Data](https://mlsanity.com/paper/2303.12291/) (2023)

## Built on by (most cited first, 18 of 18)

- [Bias Testing and Mitigation in LLM-based Code Generation](https://mlsanity.com/paper/2309.14345/) (2023)
- [OxonFair: A Flexible Toolkit for Algorithmic Fairness](https://mlsanity.com/paper/2407.13710/) (2024)
- [ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods](https://mlsanity.com/paper/2409.16965/) (2024)
- [A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems](https://mlsanity.com/paper/2407.12710/) (2024)
- [Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspective](https://mlsanity.com/paper/2501.14710/) (2025)
- [The Costs of Pretending That There Are Data-Generating Probability Distributions in the Social World](https://mlsanity.com/paper/2407.17395/) (2024)
- [Post-processing fairness with minimal changes](https://mlsanity.com/paper/2408.15096/) (2024)
- [Minority Collective Action for User-Side Fairness](https://mlsanity.com/paper/2508.15374/) (2025)
- [The Disparate Benefits of Deep Ensembles](https://mlsanity.com/paper/2410.13831/) (2024)
- [Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond](https://mlsanity.com/paper/2507.08866/) (2025)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness](https://mlsanity.com/paper/2510.22363/) (2025)
- [FROC: Building Fair ROC from a Trained Classifier](https://mlsanity.com/paper/2412.14724/) (2024)
- [Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity](https://mlsanity.com/paper/2505.16638/) (2025)
- [Back to the Drawing Board for Fair Representation Learning](https://mlsanity.com/paper/2405.18161/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [LLM-Augmented Computational Phenotyping of Long Covid](https://mlsanity.com/paper/2603.18115/) (2026)
- [FairBED: A Bayesian Experimental Design Approach to Gathering Fairer Data](https://mlsanity.com/paper/2606.23515/) (2026)

## Abstract (arXiv)

Seven years ago, researchers proposed a postprocessing method to equalize the error rates of a model across different demographic groups. The work launched hundreds of papers purporting to improve over the postprocessing baseline. We empirically evaluate these claims through thousands of model evaluations on several tabular datasets. We find that the fairness-accuracy Pareto frontier achieved by postprocessing contains all other methods we were feasibly able to evaluate. In doing so, we address two common methodological errors that have confounded previous observations. One relates to the comparison of methods with different unconstrained base models. The other concerns methods achieving different levels of constraint relaxation. At the heart of our study is a simple idea we call unprocessing that roughly corresponds to the inverse of postprocessing. Unprocessing allows for a direct comparison of methods using different underlying models and levels of relaxation.