Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy

NeurIPSSpotlight2025

Authors
Xiang Li, Chendi Wang, Buxin Su, Qi Long, Weijie J Su
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

differential privacy federated learning privacy

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive