Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

Author name not available (Why is that?)

Publication date: 10 February 2022

Abstract: Large-scale machine learning systems often involve data distributed across a collection of users. Federated learning algorithms leverage this structure by communicating model updates to a central server, rather than entire datasets. In this paper, we study stochastic optimization algorithms for a personalized federated learning setting involving local and global models subject to user-level (joint) differential privacy. While learning a private global model induces a cost of privacy, local learning is perfectly private. We provide generalization guarantees showing that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.

Has companion code repository: https://github.com/albietz/ppsgd

This page was built for publication: Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6390772)