# Intra-Processing Methods for Debiasing Neural Networks

arXiv: https://arxiv.org/abs/2006.08564 · HTML: https://mlsanity.com/paper/2006.08564/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 27 of 27)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks](https://mlsanity.com/paper/2402.11137/) (2024)
- [Estimating and Improving Fairness with Adversarial Learning](https://mlsanity.com/paper/2103.04243/) (2021)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods](https://mlsanity.com/paper/2208.00781/) (2022)
- [Improving Fairness using Vision-Language Driven Image Augmentation](https://mlsanity.com/paper/2311.01573/) (2023)
- [OmiEmbed: a unified multi-task deep learning framework for multi-omics data](https://mlsanity.com/paper/2102.02669/) (2021)
- [Robustness Disparities in Commercial Face Detection](https://mlsanity.com/paper/2108.12508/) (2021)
- [Should We Attend More or Less? Modulating Attention for Fairness](https://mlsanity.com/paper/2305.13088/) (2023)
- [Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies](https://mlsanity.com/paper/2312.01509/) (2023)
- [Comparing Human and Machine Bias in Face Recognition](https://mlsanity.com/paper/2110.08396/) (2021)
- [Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions](https://mlsanity.com/paper/2107.09546/) (2021)
- [Robustness Disparities in Face Detection](https://mlsanity.com/paper/2211.15937/) (2022)
- [Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale](https://mlsanity.com/paper/2206.14853/) (2022)
- [Are Commercial Face Detection Models as Biased as Academic Models?](https://mlsanity.com/paper/2201.10047/) (2022)
- [Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access](https://mlsanity.com/paper/2302.01385/) (2023)
- [UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks](https://mlsanity.com/paper/2302.12538/) (2023)
- [GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2408.16700/) (2024)
- [Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations](https://mlsanity.com/paper/2305.20020/) (2023)
- [DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision](https://mlsanity.com/paper/2505.05492/) (2025)
- [Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics](https://mlsanity.com/paper/2303.14411/) (2023)
- [Personalised Drug Identifier for Cancer Treatment with Transformers using Auxiliary Information](https://mlsanity.com/paper/2402.10551/) (2024)
- [Reducing Bias in Pre-trained Models by Tuning while Penalizing Change](https://mlsanity.com/paper/2404.12292/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [Simulating Biases for Interpretable Fairness in Offline and Online Classifiers](https://mlsanity.com/paper/2507.10154/) (2025)

## Abstract (arXiv)

As deep learning models become tasked with more and more decisions that impact human lives, such as criminal recidivism, loan repayment, and face recognition for law enforcement, bias is becoming a growing concern. Debiasing algorithms are typically split into three paradigms: pre-processing, in-processing, and post-processing. However, in computer vision or natural language applications, it is common to start with a large generic model and then fine-tune to a specific use-case. Pre- or in-processing methods would require retraining the entire model from scratch, while post-processing methods only have black-box access to the model, so they do not leverage the weights of the trained model. Creating debiasing algorithms specifically for this fine-tuning use-case has largely been neglected. In this work, we initiate the study of a new paradigm in debiasing research, intra-processing, which sits between in-processing and post-processing methods. Intra-processing methods are designed specifically to debias large models which have been trained on a generic dataset and fine-tuned on a more specific task. We show how to repurpose existing in-processing methods for this use-case, and we also propose three baseline algorithms: random perturbation, layerwise optimization, and adversarial fine-tuning. All of our techniques can be used for all popular group fairness measures such as equalized odds or statistical parity difference. We evaluate these methods across three popular datasets from the AIF360 toolkit, as well as on the CelebA faces dataset. Our code is available at https://github.com/abacusai/intraprocessing_debiasing.