# Multiaccurate Proxies for Downstream Fairness

arXiv: https://arxiv.org/abs/2107.04423 · HTML: https://mlsanity.com/paper/2107.04423/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Minimax Pareto Fairness: A Multi Objective Perspective](https://mlsanity.com/paper/2011.01821/) (2020)
- [Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved](https://mlsanity.com/paper/1811.11154/) (2018)
- [Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination](https://mlsanity.com/paper/1906.00285/) (2019)
- [Robust Optimization for Fairness with Noisy Protected Groups](https://mlsanity.com/paper/2002.09343/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Moment Multicalibration for Uncertainty Estimation](https://mlsanity.com/paper/2008.08037/) (2020)
- [Equalized odds postprocessing under imperfect group information](https://mlsanity.com/paper/1906.03284/) (2019)
- [Blind Justice: Fairness with Encrypted Sensitive Attributes](https://mlsanity.com/paper/1806.03281/) (2018)
- [Downstream Effects of Affirmative Action](https://mlsanity.com/paper/1808.09004/) (2018)
- [Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information](https://mlsanity.com/paper/2102.08410/) (2021)
- [Mitigating Bias in Set Selection with Noisy Protected Attributes](https://mlsanity.com/paper/2011.04219/) (2020)
- [Individual Fairness in Pipelines](https://mlsanity.com/paper/2004.05167/) (2020)
- [Fair Pipelines](https://mlsanity.com/paper/1707.00391/) (2017)
- [Lexicographically Fair Learning: Algorithms and Generalization](https://mlsanity.com/paper/2102.08454/) (2021)

## Built on by (most cited first, 17 of 17)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [The Rich Get Richer: Disparate Impact of Semi-Supervised Learning](https://mlsanity.com/paper/2110.06282/) (2021)
- [Simple and near-optimal algorithms for hidden stratification and multi-group learning](https://mlsanity.com/paper/2112.12181/) (2021)
- [Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making](https://mlsanity.com/paper/2302.06503/) (2023)
- [Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes](https://mlsanity.com/paper/2210.03175/) (2022)
- [Multicalibrated Regression for Downstream Fairness](https://mlsanity.com/paper/2209.07312/) (2022)
- [Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes](https://mlsanity.com/paper/2211.09101/) (2022)
- [Fairness without Sensitive Attributes via Knowledge Sharing](https://mlsanity.com/paper/2409.18470/) (2024)
- [Fairness Under Demographic Scarce Regime](https://mlsanity.com/paper/2307.13081/) (2023)
- [Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning](https://mlsanity.com/paper/2311.18190/) (2023)
- [Distributionally Robust Data Join](https://mlsanity.com/paper/2202.05797/) (2022)
- [Context matters for fairness -- a case study on the effect of spatial distribution shifts](https://mlsanity.com/paper/2206.11436/) (2022)
- ["You Can't Fix What You Can't Measure": Privately Measuring Demographic Performance Disparities in Federated Learning](https://mlsanity.com/paper/2206.12183/) (2022)
- [Multiaccuracy and Multicalibration via Proxy Groups](https://mlsanity.com/paper/2503.02870/) (2025)
- [Safe Fairness Guarantees Without Demographics in Classification: Spectral Uncertainty Set Perspective](https://mlsanity.com/paper/2602.11785/) (2026)
- [Balanced Filtering via Disclosure-Controlled Proxies](https://mlsanity.com/paper/2306.15083/) (2023)
- [Dancing in the Shadows: Harnessing Ambiguity for Fairer Classifiers](https://mlsanity.com/paper/2406.19066/) (2024)

## Abstract (arXiv)

We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time -- in other words, how can we train a model to be fair by race when we don't have data about race? We adopt a fairness pipeline perspective, in which an "upstream" learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general "downstream" learner -- with minimal assumptions on their prediction task -- to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies, and conduct an experimental evaluation. In general, multiaccuracy is much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.