Year: 2025
Type: conference-paper
Abstract: While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. In this work, we propose Multi-Tier Federated Learning with Multi-Tier Differential Privacy ($\mathrm{M}^{2} \text{FDP}$), a DP-enhanced FL methodology for jointly optimizing privacy and performance in hierarchical networks. One of the key concepts of$M^{2} F D P$is to adapt DP noise injection according to different tiers of an established edge/fog hierarchy (e.g., edge devices, intermediate nodes, and other layers up to cloud servers) according to the trust models within particular subnetworks. We conduct a comprehensive analysis of the convergence behavior of$M^{2} F D P$, revealing conditions on parameter tuning under which the training process converges sublinearly to a finite stationarity gap that depends on the network hierarchy, trust model, and target privacy level. Subsequent numerical evaluations demonstrate that$M^{2} F D P$obtains substantial improvements in these metrics over baselines for different privacy budgets, and validate the impact of different system configurations.
Authors: Evan Chen, Frank Po-Chen Lin, Dong-Jun Han, Christopher G. Brinton
Institutions: Purdue University West Lafayette, Yonsei University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7084111362