mlsanityData to 14 Oct 2026

On the Fairness Impacts of Private Ensembles Models

arXiv 2305.11807 ↗First posted 19 May 2023cs.LG cs.AI cs.CYcited by 4

Not on the map. Why?

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

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

26 of 51 references.

References · 26

  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  3. 2017Renyi Differential Privacycited by 650
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2018Scalable Private Learning with PATEcited by 269
  6. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  7. 2021Deep Learning with Label Differential Privacycited by 117
  8. 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
  9. 2018Differentially Private Fair Learningcited by 76
  10. 2020Lagrangian Duality for Constrained Deep Learningcited by 74
  11. 2021Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descentcited by 73
  12. 2017Efficient Private ERM for Smooth Objectivescited by 61
14 more
  1. 2020Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacycited by 61
  2. 2019Fair Decision Making using Privacy-Protected Datacited by 58
  3. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  4. 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
  5. 2020Fair Learning with Private Demographic Datacited by 46
  6. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 33
  7. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  8. 2020FairFaceGAN: Fairness-aware Facial Image-to-Image Translationcited by 21
  9. 2018Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Casecited by 19
  10. 2022How unfair is private learning ?cited by 18
  11. 2019DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERMcited by 15
  12. 2021AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methodscited by 15
  13. 2022Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Searchcited by 15
  14. 2021A Fairness Analysis on Private Aggregation of Teacher Ensemblescited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2023On The Fairness Impacts of Hardware Selection in Machine Learningcited by 2
  2. 2024Privacy at a Price: Exploring its Dual Impact on AI Fairnesscited by 1
  3. 2025Private Rate-Constrained Optimization with Applications to Fair Learningcited by 1
  4. 2024Differentially Private Data Release on Graphs: Inefficiencies and Unfairnesscited by 0