mlsanityData to 7 Oct 2026

Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach

arXiv 2009.12562 ↗First posted 26 Sep 2020cs.LG cs.AI cs.CRcited by 53

Not on the map. Why?

Abstract (arXiv)

A critical concern in data-driven decision making is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the sensitive attributes is essential, while, in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints while guaranteeing the privacy of sensitive attributes. The paper analyses the tension between accuracy, privacy, and fairness and the experimental evaluation illustrates the benefits of the proposed model on several prediction tasks.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 9; 2023: 12; 2024: 11; 2025: 4; 2026: 4.

53 papers.

Sort:

By area:

  1. 2021End-to-End Constrained Optimization Learning: A Surveycited by 154
  2. 2021Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Datacited by 48
  3. 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
  4. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  5. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  6. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?cited by 32
  7. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  8. 2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
  9. 2021A Stochastic Optimization Framework for Fair Risk Minimizationcited by 26
  10. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  11. 2021Learning Hard Optimization Problems: A Data Generation Perspectivecited by 21
  12. 2021Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Methodcited by 20
38 more
  1. 2022Differential Privacy has Bounded Impact on Fairness in Classificationcited by 18
  2. 2022Stochastic Differentially Private and Fair Learningcited by 16
  3. 2023Unraveling Privacy Risks of Individual Fairness in Graph Neural Networkscited by 16
  4. 2023Resilient Constrained Learningcited by 15
  5. 2021A Fairness Analysis on Private Aggregation of Teacher Ensemblescited by 11
  6. 2022The Impact of Differential Privacy on Group Disparity Mitigationcited by 11
  7. 2023Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utilitycited by 10
  8. 2021Federated Learning Meets Fairness and Differential Privacycited by 9
  9. 2023Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approachcited by 9
  10. 2024Near-Optimal Solutions of Constrained Learning Problemscited by 9
  11. 2022SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensemblescited by 8
  12. 2021DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?cited by 6
  13. 2022Fairness Increases Adversarial Vulnerabilitycited by 5
  14. 2024Differentially Private Post-Processing for Fair Regressioncited by 5
  15. 2023On the Fairness Impacts of Private Ensembles Modelscited by 4
  16. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  17. 2023On the Impact of Multi-dimensional Local Differential Privacy on Fairnesscited by 4
  18. 2023SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learningcited by 4
  19. 2024Differentially Private Clustered Federated Learningcited by 4
  20. 2025PROPEL: Supervised and Reinforcement Learning for Large-Scale Supply Chain Planningcited by 4
  21. 2023FairDP: Certified Fairness with Differential Privacycited by 3
  22. 2024Regulation Games for Trustworthy Machine Learningcited by 3
  23. 2024Differentially Private Fair Binary Classificationscited by 3
  24. 2024PFGuard: A Generative Framework with Privacy and Fairness Safeguardscited by 3
  25. 2023On The Fairness Impacts of Hardware Selection in Machine Learningcited by 2
  26. 2024Compact Optimality Verification for Optimization Proxiescited by 2
  27. 2024Combining Machine Learning Defenses without Conflictscited by 2
  28. 2024Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacycited by 1
  29. 2026Learning to Optimize by Differentiable Programmingcited by 1
  30. 2021Differentially Empirical Risk Minimization under the Fairness Lenscited by 0
  31. 2021F3: Fair and Federated Face Attribute Classification with Heterogeneous Datacited by 0
  32. 2022The intersection of machine learning with forecasting and optimisation: theory and applicationscited by 0
  33. 2023Fairly Private: Investigating The Fairness of Visual Privacy Preservation Algorithmscited by 0
  34. 2024Differentially Private Data Release on Graphs: Inefficiencies and Unfairnesscited by 0
  35. 2024SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AIcited by 0
  36. 2025On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learningcited by 0
  37. 2025FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utilitycited by 0
  38. 2025Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classificationcited by 0

50 most cited of 53 All 53 (JSON)