Stochastic Differentially Private and Fair Learning

2022-10-17 · Andrew Lowy, Devansh Gupta, Meisam Razaviyayn

Machine learning models are increasingly used in high-stakes decision-making systems. In such applications, a major concern is that these models sometimes discriminate against certain demographic groups such as individuals with certain race, gender, or age. Another major concern in these applications is the violation of the privacy of users. While fair learning algorithms have been developed to mitigate discrimination issues, these algorithms can still leak sensitive information, such as individuals' health or financial records. Utilizing the notion of differential privacy (DP), prior works aimed at developing learning algorithms that are both private and fair. However, existing algorithms for DP fair learning are either not guaranteed to converge or require full batch of data in each iteration of the algorithm to converge. In this paper, we provide the first stochastic differentially private algorithm for fair learning that is guaranteed to converge. Here, the term "stochastic" refers to the fact that our proposed algorithm converges even when minibatches of data are used at each iteration (i.e. stochastic optimization). Our framework is flexible enough to permit different fairness notions, including demographic parity and equalized odds. In addition, our algorithm can be applied to non-binary classification tasks with multiple (non-binary) sensitive attributes. As a byproduct of our convergence analysis, we provide the first utility guarantee for a DP algorithm for solving nonconvex-strongly concave min-max problems. Our numerical experiments show that the proposed algorithm consistently offers significant performance gains over the state-of-the-art baselines, and can be applied to larger scale problems with non-binary target/sensitive attributes.

📄 PDF Abstract BibTeX arXiv:2210.08781

Code (1)

devanshgupta160/stochastic-differentially-private-and-fair-learning 공식 구현 pytorch

Tasks

Binary Classification Decision Making Fairness Stochastic Optimization

Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD

2025-10-02 · Lea Demelius, Dominik Kowald, Simone Kopeinik, Roman Kern 외 arxiv

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the m…

Differentially Private Empirical Risk Minimization under the Fairness Lens

2021-12-01 · NeurIPS 2021 12 · Cuong Tran, My Dinh, Ferdinando Fioretto

Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, …

Fairness

Differentially Empirical Risk Minimization under the Fairness Lens

2021-06-04 · Cuong Tran, My H. Dinh, Ferdinando Fioretto

Fairness

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

2020-07-18 · Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu 외

This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness,…

Deep Learning Fairness Generative Adversarial Network Privacy Preserving+1

Fairness-aware Differentially Private Collaborative Filtering

2023-03-16 · Zhenhuan Yang, Yingqiang Ge, Congzhe Su, Dingxian Wang 외

Recently, there has been an increasing adoption of differential privacy guided algorithms for privacy-preserving machine learning tasks. However, the use of such algorithms comes with trade-offs in terms of algorithmic f…

Collaborative Filtering Fairness Privacy Preserving