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

2026-04-12

AI Summary

This work addresses the challenge of jointly designing differential privacy defenses and incentive mechanisms in resource-constrained federated learning. It proposes FEDBUD, a novel framework that uniquely integrates both data contribution volume and noise level into the incentive mechanism. The interaction between the cloud server and edge nodes is modeled as a two-stage Stackelberg game: the server offers monetary payments to incentivize participation, while each edge node autonomously optimizes its data contribution and privacy-preserving noise addition. By leveraging mean-field estimators and virtual queue techniques, the framework computes a Nash equilibrium that achieves co-optimization of privacy guarantees and model utility. Experimental results on real-world datasets demonstrate that FEDBUD significantly outperforms baseline approaches, offering superior trade-offs between model performance and the balance of privacy protection with participant incentives.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Privacy-enhancing technologies

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.

Problem

• Federated Learning
• Privacy Preservation
• Incentive Mechanism
• Differential Privacy
• Resource Constraints

Innovation

• Federated Learning
• Privacy-Incentive Tradeoff
• Stackelberg Game
• Differential Privacy
• Edge Computing