Year: 2022
Type: preprint
Abstract: As machine learning algorithms are deployed on sensitive data in critical decision making processes, it is becoming increasingly important that they are also private and fair. In this paper, we show that, when the data has a long-tailed structure, it is not possible to build accurate learning algorithms that are both private and results in higher accuracy on minority subpopulations. We further show that relaxing overall accuracy can lead to good fairness even with strict privacy requirements. To corroborate our theoretical results in practice, we provide an extensive set of experimental results using a variety of synthetic, vision (CIFAR10 and CelebA), and tabular (Law School) datasets and learning algorithms.
Source: arXiv (Cornell University)
Authors: Sanyal, Amartya, Hu, Yaxi, Yang, Fanny
Institution: ETH Zurich
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W4281761832