# NeuFair: Neural Network Fairness Repair with Dropout

arXiv: https://arxiv.org/abs/2407.04268 · HTML: https://mlsanity.com/paper/2407.04268/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 58 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 16 of 16)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [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)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [Fairness-aware Configuration of Machine Learning Libraries](https://mlsanity.com/paper/2202.06196/) (2022)
- [Causal Feature Selection for Algorithmic Fairness](https://mlsanity.com/paper/2006.06053/) (2020)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [Adaptive Fairness Improvement Based on Causality Analysis](https://mlsanity.com/paper/2209.07190/) (2022)
- [FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms](https://mlsanity.com/paper/2307.05029/) (2023)

## Built on by (most cited first, 11 of 11)

- [Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing](https://mlsanity.com/paper/2503.15815/) (2025)
- [Fairness Testing through Extreme Value Theory](https://mlsanity.com/paper/2501.11597/) (2025)
- [Advertising in AI systems: Society must be vigilant](https://mlsanity.com/paper/2505.18425/) (2025)
- [Correct-By-Construction: Certified Individual Fairness through Neural Network Training](https://mlsanity.com/paper/2508.15642/) (2025)
- [Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations](https://mlsanity.com/paper/2512.23769/) (2025)
- [AtPatch: Debugging Transformers via Hot-Fixing Over-Attention](https://mlsanity.com/paper/2601.21695/) (2026)
- [Shapley-Guided Neural Repair Approach via Derivative-Free Optimization](https://mlsanity.com/paper/2604.00422/) (2026)
- [Ethics Testing: Proactive Identification of Generative AI System Harms](https://mlsanity.com/paper/2604.22089/) (2026)
- [Provable Fairness Repair for Deep Neural Networks](https://mlsanity.com/paper/2605.19549/) (2026)
- [Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs](https://mlsanity.com/paper/2608.26209/) (2026)
- [FORGE: Verification-Gated Behavioral Repair for Generative Language Models](https://mlsanity.com/paper/2610.05190/) (2026)

## Abstract (arXiv)

This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications. While neural networks are exceptionally good at finding statistical patterns from data, they may encode and amplify existing biases from the historical data. Existing bias mitigation algorithms often require modifying the input dataset or the learning algorithms. We posit that the prevalent dropout methods that prevent over-fitting during training by randomly dropping neurons may be an effective and less intrusive approach to improve the fairness of pre-trained DNNs. However, finding the ideal set of neurons to drop is a combinatorial problem. We propose NeuFair, a family of post-processing randomized algorithms that mitigate unfairness in pre-trained DNNs via dropouts during inference after training. Our randomized search is guided by an objective to minimize discrimination while maintaining the model's utility. We show that our design of randomized algorithms is effective and efficient in improving fairness (up to 69%) with minimal or no model performance degradation. We provide intuitive explanations of these phenomena and carefully examine the influence of various hyperparameters of search algorithms on the results. Finally, we empirically and conceptually compare NeuFair to different state-of-the-art bias mitigators.