PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning

This article presents Privacy-Preserving and Quantized ADMM (PP-QADMM), a novel federated learning (FL) algorithm that is both privacy-preserving and communication-efficient, built upon the Alternating Direction Method of Multipliers (ADMM). PP-QADMM enhances privacy through three core mechanisms. F...

Full description

Saved in:
Bibliographic Details
Main Author: Anis Elgabli
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Communications Society
Subjects:
Communication-efficient federated learning
differential privacy
ADMM
stochastic quantization
secure aggregation
Online Access:https://ieeexplore.ieee.org/document/10982181/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10982181/

Similar Items