# DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?

arXiv: https://arxiv.org/abs/2106.12576 · HTML: https://mlsanity.com/paper/2106.12576/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Deep Learning with Gaussian Differential Privacy](https://mlsanity.com/paper/1911.11607/) (2019)
- [Revisiting Membership Inference Under Realistic Assumptions](https://mlsanity.com/paper/2005.10881/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Privacy in Deep Learning: A Survey](https://mlsanity.com/paper/2004.12254/) (2020)
- [Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy](https://mlsanity.com/paper/2009.06389/) (2020)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings](https://mlsanity.com/paper/2010.06667/) (2020)
- [Decision Making with Differential Privacy under a Fairness Lens](https://mlsanity.com/paper/2105.07513/) (2021)
- [On Fairness, Diversity and Randomness in Algorithmic Decision Making](https://mlsanity.com/paper/1706.10208/) (2017)
- [Differential Privacy of Hierarchical Census Data: An Optimization Approach](https://mlsanity.com/paper/2006.15673/) (2020)
- [Benchmarking Differentially Private Residual Networks for Medical Imagery](https://mlsanity.com/paper/2005.13099/) (2020)

## Built on by (most cited first, 30 of 33)

- [Mixed Differential Privacy in Computer Vision](https://mlsanity.com/paper/2203.11481/) (2022)
- [Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data](https://mlsanity.com/paper/2109.11429/) (2021)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Differential Privacy has Bounded Impact on Fairness in Classification](https://mlsanity.com/paper/2210.16242/) (2022)
- [Unlocking Accuracy and Fairness in Differentially Private Image Classification](https://mlsanity.com/paper/2308.10888/) (2023)
- [Differentially Private Model Compression](https://mlsanity.com/paper/2206.01838/) (2022)
- [The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging](https://mlsanity.com/paper/2406.13985/) (2024)
- [A Fairness Analysis on Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2109.08630/) (2021)
- [Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility](https://mlsanity.com/paper/2302.09183/) (2023)
- [SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2204.05157/) (2022)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?](https://mlsanity.com/paper/2111.13617/) (2021)
- [Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond](https://mlsanity.com/paper/2503.07501/) (2025)
- [On the Fairness Impacts of Private Ensembles Models](https://mlsanity.com/paper/2305.11807/) (2023)
- [Survey on AI Ethics: A Socio-technical Perspective](https://mlsanity.com/paper/2311.17228/) (2023)
- [A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy](https://mlsanity.com/paper/2312.11712/) (2023)
- [SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning](https://mlsanity.com/paper/2312.16191/) (2023)
- [Exploring the Unfairness of DP-SGD Across Settings](https://mlsanity.com/paper/2202.12058/) (2022)
- [Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection](https://mlsanity.com/paper/2209.04445/) (2022)
- [SoK: What Makes Private Learning Unfair?](https://mlsanity.com/paper/2501.14414/) (2025)
- [Personalized DP-SGD using Sampling Mechanisms](https://mlsanity.com/paper/2305.15165/) (2023)
- [Does Differential Privacy Impact Bias in Pretrained NLP Models?](https://mlsanity.com/paper/2410.18749/) (2024)
- [A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses](https://mlsanity.com/paper/2310.12112/) (2023)
- [Privacy at a Price: Exploring its Dual Impact on AI Fairness](https://mlsanity.com/paper/2404.09391/) (2024)
- [Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2409.01329/) (2024)
- [The Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classification](https://mlsanity.com/paper/2412.11951/) (2024)
- [Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification](https://mlsanity.com/paper/2511.18876/) (2025)
- [Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data](https://mlsanity.com/paper/2607.07471/) (2026)
- [Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inverse](https://mlsanity.com/paper/2202.08309/) (2022)

## Abstract (arXiv)

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, which leads to a significantly high drop-in model utility for sub-populations that are under-represented (minorities), compared to well-represented ones. In this work, we aim to compare PATE, another mechanism for training deep learning models using differential privacy, with DP-SGD in terms of fairness. We show that PATE does have a disparate impact too, however, it is much less severe than DP-SGD. We draw insights from this observation on what might be promising directions in achieving better fairness-privacy trade-offs.