# A Distributed Fair Machine Learning Framework with Private Demographic Data Protection

arXiv: https://arxiv.org/abs/1909.08081 · HTML: https://mlsanity.com/paper/1909.08081/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks](https://mlsanity.com/paper/2301.12951/) (2023)
- [Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity](https://mlsanity.com/paper/2211.02139/) (2022)
- [Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systems](https://mlsanity.com/paper/2309.06061/) (2023)
- [FairJob: A Real-World Dataset for Fairness in Online Systems](https://mlsanity.com/paper/2407.03059/) (2024)
- [Fairness-Driven Private Collaborative Machine Learning](https://mlsanity.com/paper/2109.14376/) (2021)
- [Preserving Fairness in AI under Domain Shift](https://mlsanity.com/paper/2301.12369/) (2023)
- [Fairguard: Harness Logic-based Fairness Rules in Smart Cities](https://mlsanity.com/paper/2302.11137/) (2023)
- [SoK: Assessing the State of Applied Federated Machine Learning](https://mlsanity.com/paper/2308.02454/) (2023)

## Abstract (arXiv)

Fair machine learning has become a significant research topic with broad societal impact. However, most fair learning methods require direct access to personal demographic data, which is increasingly restricted to use for protecting user privacy (e.g. by the EU General Data Protection Regulation). In this paper, we propose a distributed fair learning framework for protecting the privacy of demographic data. We assume this data is privately held by a third party, which can communicate with the data center (responsible for model development) without revealing the demographic information. We propose a principled approach to design fair learning methods under this framework, exemplify four methods and show they consistently outperform their existing counterparts in both fairness and accuracy across three real-world data sets. We theoretically analyze the framework, and prove it can learn models with high fairness or high accuracy, with their trade-offs balanced by a threshold variable.