# On the Fairness Impacts of Private Ensembles Models

arXiv: https://arxiv.org/abs/2305.11807 · HTML: https://mlsanity.com/paper/2305.11807/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Hyperparameter Tuning with Renyi Differential Privacy](https://mlsanity.com/paper/2110.03620/) (2021)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Lagrangian Duality for Constrained Deep Learning](https://mlsanity.com/paper/2001.09394/) (2020)
- [Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent](https://mlsanity.com/paper/2102.05855/) (2021)
- [Efficient Private ERM for Smooth Objectives](https://mlsanity.com/paper/1703.09947/) (2017)
- [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)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Fair Learning with Private Demographic Data](https://mlsanity.com/paper/2002.11651/) (2020)
- [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)
- [FairFaceGAN: Fairness-aware Facial Image-to-Image Translation](https://mlsanity.com/paper/2012.00282/) (2020)
- [Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Case](https://mlsanity.com/paper/1802.04085/) (2018)
- [How unfair is private learning ?](https://mlsanity.com/paper/2206.03985/) (2022)
- [DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM](https://mlsanity.com/paper/1906.12056/) (2019)
- [AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods](https://mlsanity.com/paper/2102.09700/) (2021)
- [Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search](https://mlsanity.com/paper/2210.02156/) (2022)
- [A Fairness Analysis on Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2109.08630/) (2021)

## Built on by (most cited first, 4 of 4)

- [On The Fairness Impacts of Hardware Selection in Machine Learning](https://mlsanity.com/paper/2312.03886/) (2023)
- [Privacy at a Price: Exploring its Dual Impact on AI Fairness](https://mlsanity.com/paper/2404.09391/) (2024)
- [Private Rate-Constrained Optimization with Applications to Fair Learning](https://mlsanity.com/paper/2505.22703/) (2025)
- [Differentially Private Data Release on Graphs: Inefficiencies and Unfairness](https://mlsanity.com/paper/2408.05246/) (2024)

## Abstract (arXiv)

The Private Aggregation of Teacher Ensembles (PATE) is a machine learning framework that enables the creation of private models through the combination of multiple "teacher" models and a "student" model. The student model learns to predict an output based on the voting of the teachers, and the resulting model satisfies differential privacy. PATE has been shown to be effective in creating private models in semi-supervised settings or when protecting data labels is a priority. This paper explores whether the use of PATE can result in unfairness, and demonstrates that it can lead to accuracy disparities among groups of individuals. The paper also analyzes the algorithmic and data properties that contribute to these disproportionate impacts, why these aspects are affecting different groups disproportionately, and offers recommendations for mitigating these effects