Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis

TL;DR

This paper introduces CEPAM, a federated learning scheme that enhances communication efficiency and privacy protection, with theoretical analysis and experimental validation of its convergence, privacy guarantees, and utility performance.

Contribution

It provides a theoretical analysis of CEPAM's privacy and convergence, and evaluates its utility and privacy trade-offs through experiments.

Findings

CEPAM achieves improved communication efficiency.

CEPAM provides customizable privacy protection.

Experimental results show competitive convergence and accuracy.

Abstract

Federated learning enables multiple parties to jointly train learning models without sharing their own underlying data, offering a practical pathway to privacy-preserving collaboration under data-governance constraints. Continued study of federated learning is essential to address key challenges in it, including communication efficiency and privacy protection between parties. A recent line of work introduced a novel approach called the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM), which achieves both objectives simultaneously. CEPAM leverages the rejection-sampled universal quantizer (RSUQ), a randomized vector quantizer whose quantization error is equivalent to a prescribed noise, which can be tuned to customize privacy protection between parties. In this work, we theoretically analyze the privacy guarantees and convergence properties of CEPAM. Moreover, we assess CEPAM's utility performance through experimental evaluations, including convergence profiles compared with other baselines, and accuracy-privacy trade-offs between different parties.