FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning

TL;DR

FEDBUD is a federated learning system that jointly optimizes privacy and incentives by modeling data volume and noise level influences, using game theory to achieve optimal strategies.

Contribution

It introduces a novel incentive and privacy optimization framework considering both data volume and noise, modeled as a Stackelberg game with real-world experimental validation.

Findings

FEDBUD effectively balances privacy and incentive concerns in federated learning.

The system achieves superior performance on real-world datasets.

Optimal strategies derived improve model performance and privacy protection.

Abstract

Federated learning has become a popular paradigm for privacy protection and edge-based machine learning. However, defending against differential attacks and devising incentive strategies remain significant bottlenecks in this field. Despite recent works on privacy-aware incentive mechanism design for federated learning, few of them consider both data volume and noise level. In this paper, we propose a novel federated learning system called FEDBUD, which combines privacy and economic concerns together by considering the joint influence of data volume and noise level on incentive strategy determination. In this system, the cloud server controls monetary payments to edge nodes, while edge nodes control data volume and noise level that potentially impact the model performance of the cloud server. To determine the mutually optimal strategies for both sides, we model FEDBUD as a two-stage Stackelberg Game and derive the Nash Equilibrium using the mean-field estimator and virtual queue. Experimental results on real-world datasets demonstrate the outstanding performance of FEDBUD.