# The Impact of Differential Privacy on Group Disparity Mitigation

arXiv: https://arxiv.org/abs/2203.02745 · HTML: https://mlsanity.com/paper/2203.02745/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 5 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data](https://mlsanity.com/paper/1508.03422/) (2015)
- [Distributionally Robust Language Modeling](https://mlsanity.com/paper/1909.02060/) (2019)
- [Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.05830/) (2015)
- [Fairness risk measures](https://mlsanity.com/paper/1901.08665/) (2019)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy](https://mlsanity.com/paper/2009.06389/) (2020)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text](https://mlsanity.com/paper/1910.08917/) (2019)
- [Differentially Private Language Models Benefit from Public Pre-training](https://mlsanity.com/paper/2009.05886/) (2020)
- [Evaluating Lottery Tickets Under Distributional Shifts](https://mlsanity.com/paper/1910.12708/) (2019)
- [Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks](https://mlsanity.com/paper/2102.05975/) (2021)
- [How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning](https://mlsanity.com/paper/2007.09370/) (2020)
- [Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning](https://mlsanity.com/paper/1511.09337/) (2015)

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

- [Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent](https://mlsanity.com/paper/2206.02617/) (2022)
- [DP-NMT: Scalable Differentially-Private Machine Translation](https://mlsanity.com/paper/2311.14465/) (2023)
- [Trade-Offs Between Fairness and Privacy in Language Modeling](https://mlsanity.com/paper/2305.14936/) (2023)
- [LLM Bias Detection and Mitigation through the Lens of Desired Distributions](https://mlsanity.com/paper/2510.06354/) (2025)
- [Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models](https://mlsanity.com/paper/2308.08774/) (2023)
- [Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD](https://mlsanity.com/paper/2510.01744/) (2025)
- [Characterizing Stereotypical Bias from Privacy-preserving Pre-Training](https://mlsanity.com/paper/2407.00764/) (2024)
- [Private and interpretable clinical prediction with quantum-inspired tensor train models](https://mlsanity.com/paper/2602.06110/) (2026)
- [Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems](https://mlsanity.com/paper/2605.24458/) (2026)
- [Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms](https://mlsanity.com/paper/2607.14607/) (2026)
- [The Privacy-Hallucination Tradeoff in Differentially Private Language Models](https://mlsanity.com/paper/2609.00492/) (2026)

## Abstract (arXiv)

The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in this area has been restricted to computer vision and risk assessment. In this paper, we evaluate the impact of differential privacy on fairness across four tasks, focusing on how attempts to mitigate privacy violations and between-group performance differences interact: Does privacy inhibit attempts to ensure fairness? To this end, we train (varepsilon,δ)-differentially private models with empirical risk minimization and group distributionally robust training objectives. Consistent with previous findings, we find that differential privacy increases between-group performance differences in the baseline setting; but more interestingly, differential privacy reduces between-group performance differences in the robust setting. We explain this by reinterpreting differential privacy as regularization.