Incentive-boosted Federated Crowdsourcing

TL;DR

This paper introduces iFedCrowd, a federated crowdsourcing framework that enhances privacy and quality through local data processing, encrypted model sharing, and an incentive mechanism modeled as a Stackelberg game, proven effective through experiments.

Contribution

The paper proposes iFedCrowd, a novel federated crowdsourcing approach combining privacy-preserving data sharing with an incentive mechanism modeled as a Stackelberg game.

Findings

iFedCrowd achieves high-quality global models with privacy protection.

The incentive mechanism effectively motivates workers to contribute fresh data.

Experimental results demonstrate improved efficiency and model accuracy.

Abstract

Crowdsourcing is a favorable computing paradigm for processing computer-hard tasks by harnessing human intelligence. However, generic crowdsourcing systems may lead to privacy-leakage through the sharing of worker data. To tackle this problem, we propose a novel approach, called iFedCrowd (incentive-boosted Federated Crowdsourcing), to manage the privacy and quality of crowdsourcing projects. iFedCrowd allows participants to locally process sensitive data and only upload encrypted training models, and then aggregates the model parameters to build a shared server model to protect data privacy. To motivate workers to build a high-quality global model in an efficacy way, we introduce an incentive mechanism that encourages workers to constantly collect fresh data to train accurate client models and boosts the global model training. We model the incentive-based interaction between the crowdsourcing platform and participating workers as a Stackelberg game, in which each side maximizes its own profit. We derive the Nash Equilibrium of the game to find the optimal solutions for the two sides. Experimental results confirm that iFedCrowd can complete secure crowdsourcing projects with high quality and efficiency.