# Pruning has a disparate impact on model accuracy

arXiv: https://arxiv.org/abs/2205.13574 · HTML: https://mlsanity.com/paper/2205.13574/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 56 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [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)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://mlsanity.com/paper/2003.02389/) (2020)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [What Do Compressed Deep Neural Networks Forget?](https://mlsanity.com/paper/1911.05248/) (2019)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1804.03294/) (2018)
- [Lagrangian Duality for Constrained Deep Learning](https://mlsanity.com/paper/2001.09394/) (2020)
- [Sparse DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1810.09619/) (2018)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation](https://mlsanity.com/paper/2110.03036/) (2021)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression](https://mlsanity.com/paper/2109.03228/) (2021)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [Decision Making with Differential Privacy under a Fairness Lens](https://mlsanity.com/paper/2105.07513/) (2021)
- [The Rich Get Richer: Disparate Impact of Semi-Supervised Learning](https://mlsanity.com/paper/2110.06282/) (2021)
- [Towards Compact and Robust Deep Neural Networks](https://mlsanity.com/paper/1906.06110/) (2019)
- [Prune Responsibly](https://mlsanity.com/paper/2009.09936/) (2020)
- [Can Model Compression Improve NLP Fairness](https://mlsanity.com/paper/2201.08542/) (2022)

## Built on by (most cited first, 30 of 44)

- [Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging](https://mlsanity.com/paper/2306.16788/) (2023)
- [Superficial Safety Alignment Hypothesis](https://mlsanity.com/paper/2410.10862/) (2024)
- [Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm](https://mlsanity.com/paper/2206.02976/) (2022)
- [On Fairness of Low-Rank Adaptation of Large Models](https://mlsanity.com/paper/2405.17512/) (2024)
- [Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions](https://mlsanity.com/paper/2301.07966/) (2023)
- [Zero-shot Quantization: A Comprehensive Survey](https://mlsanity.com/paper/2505.09188/) (2025)
- [Quantifying and mitigating the impact of label errors on model disparity metrics](https://mlsanity.com/paper/2310.02533/) (2023)
- [Balancing Act: Constraining Disparate Impact in Sparse Models](https://mlsanity.com/paper/2310.20673/) (2023)
- [DRoP: Distributionally Robust Data Pruning](https://mlsanity.com/paper/2404.05579/) (2024)
- [LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging](https://mlsanity.com/paper/2406.12837/) (2024)
- [BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning](https://mlsanity.com/paper/2408.06890/) (2024)
- [Fairness Increases Adversarial Vulnerability](https://mlsanity.com/paper/2211.11835/) (2022)
- [FairDP: Certified Fairness with Differential Privacy](https://mlsanity.com/paper/2305.16474/) (2023)
- [Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities](https://mlsanity.com/paper/2406.01757/) (2024)
- [Uncovering the Hidden Cost of Model Compression](https://mlsanity.com/paper/2308.14969/) (2023)
- [FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation](https://mlsanity.com/paper/2410.17358/) (2024)
- [Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives](https://mlsanity.com/paper/2502.16841/) (2025)
- [On The Fairness Impacts of Hardware Selection in Machine Learning](https://mlsanity.com/paper/2312.03886/) (2023)
- [You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models](https://mlsanity.com/paper/2410.20265/) (2024)
- [An Efficient Training Algorithm for Models with Block-wise Sparsity](https://mlsanity.com/paper/2503.21928/) (2025)
- [Explaining How Quantization Disparately Skews a Model](https://mlsanity.com/paper/2509.07222/) (2025)
- [Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores](https://mlsanity.com/paper/2512.01080/) (2025)
- [Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI](https://mlsanity.com/paper/2605.08137/) (2026)
- [Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks](https://mlsanity.com/paper/2310.08073/) (2023)
- [Integrating Fairness and Model Pruning Through Bi-level Optimization](https://mlsanity.com/paper/2312.10181/) (2023)
- [CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographics](https://mlsanity.com/paper/2404.19725/) (2024)
- [Fisher-aware Quantization for DETR Detectors with Critical-category Objectives](https://mlsanity.com/paper/2407.03442/) (2024)
- [MicroNAS: An Automated Framework for Developing a Fall Detection System](https://mlsanity.com/paper/2504.07397/) (2025)
- [MGS: Markov Greedy Sums for Accurate Low-Bitwidth Floating-Point Accumulation](https://mlsanity.com/paper/2504.09072/) (2025)
- [Decoupling Generalizability and Membership Privacy Risks in Neural Networks](https://mlsanity.com/paper/2602.02296/) (2026)

## Abstract (arXiv)

Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy. This paper shows that pruning may create or exacerbate disparate impacts. The paper sheds light on the factors to cause such disparities, suggesting differences in gradient norms and distance to decision boundary across groups to be responsible for this critical issue. It analyzes these factors in detail, providing both theoretical and empirical support, and proposes a simple, yet effective, solution that mitigates the disparate impacts caused by pruning.