Incentive-Boosted Federated Crowdsourcing
Keywords:HAI: Crowdsourcing, HAI: Human-in-the-Loop Machine Learning, ML: Distributed Machine Learning & Federated Learning, ML: Multi-Class/Multi-Label Learning & Extreme Classification, ML: Multi-Instance/Multi-View Learning
AbstractCrowdsourcing 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.
How to Cite
Kang, X., Yu, G., Wang, J., Guo, W., Domeniconi, C., & Zhang, J. (2023). Incentive-Boosted Federated Crowdsourcing. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6021-6029. https://doi.org/10.1609/aaai.v37i5.25744
AAAI Technical Track on Humans and AI