SoK: What Makes Private Learning Unfair?
Kai Yao, Marc Juarez

TL;DR
This paper surveys how differential privacy in machine learning can unintentionally worsen disparities across groups, analyzing contributing factors and their roles within the training process.
Contribution
It provides the first comprehensive taxonomy of factors influencing fairness disparities in private learning and analyzes their causal impact.
Findings
Dataset and distribution factors are key in disparity occurrence
Differential privacy mechanisms can amplify existing inequalities
Understanding these factors is crucial for mitigation strategies
Abstract
Differential privacy has emerged as the most studied framework for privacy-preserving machine learning. However, recent studies show that enforcing differential privacy guarantees can not only significantly degrade the utility of the model, but also amplify existing disparities in its predictive performance across demographic groups. Although there is extensive research on the identification of factors that contribute to this phenomenon, we still lack a complete understanding of the mechanisms through which differential privacy exacerbates disparities. The literature on this problem is muddled by varying definitions of fairness, differential privacy mechanisms, and inconsistent experimental settings, often leading to seemingly contradictory results. This survey provides the first comprehensive overview of the factors that contribute to the disparate effect of training models with…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGlobal Educational Reforms and Inequalities
