# Blackbox Post-Processing for Multiclass Fairness

arXiv: https://arxiv.org/abs/2201.04461 · HTML: https://mlsanity.com/paper/2201.04461/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 12 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Short-term Intervention for Long-term Fairness in the Labor Market](https://mlsanity.com/paper/1712.00064/) (2017)
- [Achieving Equalized Odds by Resampling Sensitive Attributes](https://mlsanity.com/paper/2006.04292/) (2020)
- [Unbiased Subdata Selection for Fair Classification: A Unified Framework and Scalable Algorithms](https://mlsanity.com/paper/2012.12356/) (2020)

## Built on by (most cited first, 14 of 14)

- [Fair Generalized Linear Models with a Convex Penalty](https://mlsanity.com/paper/2206.09076/) (2022)
- [Learning Optimal Fair Scoring Systems for Multi-Class Classification](https://mlsanity.com/paper/2304.05023/) (2023)
- [Detecting and Mitigating Algorithmic Bias in Binary Classification using Causal Modeling](https://mlsanity.com/paper/2310.12421/) (2023)
- [Evaluating Model Bias Requires Characterizing its Mistakes](https://mlsanity.com/paper/2407.10633/) (2024)
- [Modeling Quality and Machine Learning Pipelines through Extended Feature Models](https://mlsanity.com/paper/2207.07528/) (2022)
- [Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations](https://mlsanity.com/paper/2305.20020/) (2023)
- [Mitigating Nonlinear Algorithmic Bias in Binary Classification](https://mlsanity.com/paper/2312.05429/) (2023)
- [Biased Heritage: How Datasets Shape Models in Facial Expression Recognition](https://mlsanity.com/paper/2503.03446/) (2025)
- [Disparate Conditional Prediction in Multiclass Classifiers](https://mlsanity.com/paper/2206.03234/) (2022)
- [Migrate Demographic Group For Fair GNNs](https://mlsanity.com/paper/2306.04212/) (2023)
- [Fair Class-Incremental Learning using Sample Weighting](https://mlsanity.com/paper/2410.01324/) (2024)
- [Alpha and Prejudice: Improving α-sized Worst-case Fairness via Intrinsic Reweighting](https://mlsanity.com/paper/2411.03068/) (2024)
- [Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling](https://mlsanity.com/paper/2501.07885/) (2025)
- [A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks](https://mlsanity.com/paper/2603.21393/) (2026)

## Abstract (arXiv)

Applying standard machine learning approaches for classification can produce unequal results across different demographic groups. When then used in real-world settings, these inequities can have negative societal impacts. This has motivated the development of various approaches to fair classification with machine learning models in recent years. In this paper, we consider the problem of modifying the predictions of a blackbox machine learning classifier in order to achieve fairness in a multiclass setting. To accomplish this, we extend the 'post-processing' approach in Hardt et al. 2016, which focuses on fairness for binary classification, to the setting of fair multiclass classification. We explore when our approach produces both fair and accurate predictions through systematic synthetic experiments and also evaluate discrimination-fairness tradeoffs on several publicly available real-world application datasets. We find that overall, our approach produces minor drops in accuracy and enforces fairness when the number of individuals in the dataset is high relative to the number of classes and protected groups.