# A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models

arXiv: https://arxiv.org/abs/2106.12887 · HTML: https://mlsanity.com/paper/2106.12887/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 70 references that are in the map.
- First posted on arXiv 6 Jun 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [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)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy](https://mlsanity.com/paper/1912.07726/) (2019)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [On Robustness and Transferability of Convolutional Neural Networks](https://mlsanity.com/paper/2007.08558/) (2020)
- [A Confidence-Based Approach for Balancing Fairness and Accuracy](https://mlsanity.com/paper/1601.05764/) (2016)
- [Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?](https://mlsanity.com/paper/1912.01094/) (2019)
- [A statistical framework for fair predictive algorithms](https://mlsanity.com/paper/1610.08077/) (2016)

## Built on by (most cited first, 19 of 19)

- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Extremely Simple Activation Shaping for Out-of-Distribution Detection](https://mlsanity.com/paper/2209.09858/) (2022)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing](https://mlsanity.com/paper/2207.10384/) (2022)
- [On Data Scaling in Masked Image Modeling](https://mlsanity.com/paper/2206.04664/) (2022)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Multicalibrated Regression for Downstream Fairness](https://mlsanity.com/paper/2209.07312/) (2022)
- [Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks](https://mlsanity.com/paper/2204.04440/) (2022)
- [A Reduction to Binary Approach for Debiasing Multiclass Datasets](https://mlsanity.com/paper/2205.15860/) (2022)
- [Mind the Graph When Balancing Data for Fairness or Robustness](https://mlsanity.com/paper/2406.17433/) (2024)
- [Fairness-aware Vision Transformer via Debiased Self-Attention](https://mlsanity.com/paper/2301.13803/) (2023)
- [Fair Wrapping for Black-box Predictions](https://mlsanity.com/paper/2201.12947/) (2022)
- [Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale](https://mlsanity.com/paper/2206.14853/) (2022)
- [Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities](https://mlsanity.com/paper/2403.18196/) (2024)
- [Layer-Stack Temperature Scaling](https://mlsanity.com/paper/2211.10193/) (2022)
- [Achievable Fairness on Your Data With Utility Guarantees](https://mlsanity.com/paper/2402.17106/) (2024)
- [Personalised Drug Identifier for Cancer Treatment with Transformers using Auxiliary Information](https://mlsanity.com/paper/2402.10551/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)

## Abstract (arXiv)

We present a scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes risk. We empirically validate its advantages on standard benchmark datasets across both classical algorithms as well as modern DNN architectures and demonstrate that it outperforms previous post-processing methods while performing on par with in-processing. In addition, we show that the proposed algorithm is particularly effective for models trained at scale where post-processing is a natural and practical choice.