# Inference-Time Rule Eraser: Fair Recognition via Distilling and Removing Biased Rules

arXiv: https://arxiv.org/abs/2404.04814 · HTML: https://mlsanity.com/paper/2404.04814/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 65 references that are in the map.
- First posted on arXiv 7 Apr 2024.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [Beyond Parity: Fairness Objectives for Collaborative Filtering](https://mlsanity.com/paper/1705.08804/) (2017)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Deep Feature Interpolation for Image Content Changes](https://mlsanity.com/paper/1611.05507/) (2016)
- [Bias Mitigation Post-processing for Individual and Group Fairness](https://mlsanity.com/paper/1812.06135/) (2018)
- [Fair Contrastive Learning for Facial Attribute Classification](https://mlsanity.com/paper/2203.16209/) (2022)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning](https://mlsanity.com/paper/2206.06122/) (2022)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Fairness Reprogramming](https://mlsanity.com/paper/2209.10222/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Multi-Component Reward Function with Policy Gradient for Automated Feature Selection with Dynamic Regularization and Bias Mitigation](https://mlsanity.com/paper/2510.09705/) (2025)

## Abstract (arXiv)

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal justice. Traditional approaches to addressing this issue involve retraining or fine-tuning neural networks with fairness-aware optimization objectives. However, these methods can be impractical due to significant computational resources, complex industrial tests, and the associated CO2 footprint. Additionally, regular users often fail to fine-tune models because they lack access to model parameters In this paper, we introduce the Inference-Time Rule Eraser (Eraser), a novel method designed to address fairness concerns by removing biased decision-making rules from deployed models during inference without altering model weights. We begin by establishing a theoretical foundation for modifying model outputs to eliminate biased rules through Bayesian analysis. Next, we present a specific implementation of Eraser that involves two stages: (1) distilling the biased rules from the deployed model into an additional patch model, and (2) removing these biased rules from the output of the deployed model during inference. Extensive experiments validate the effectiveness of our approach, showcasing its superior performance in addressing fairness concerns in AI systems.