Timeliness-Selective Incentive Federated Crowdsourcing

Xiaoqian Jiang, Haiyang Diao, Cangqi Zhou, Jing Zhang

Abstract: Crowdsourcing offers an efficient means of gathering labeled data and training machine learning models. However, the exposure of crowd workers to potential privacy breaches during data collection diminishes their willingness to participate. This paper proposes TsIFedCrowd, a novel incentive mechanism within the federated learning paradigm, aimed at mitigating privacy risks for crowd workers while achieving high-quality crowdsourced data and learning models at minimal expense. TsIFedCrowd enables clients to retain privacy-sensitive data locally, requiring only the upload of trained models to the server, which aggregates them into a global model. By modeling the federated crowdsourcing process as a two-stage Stackelberg game, TsIFedCrowd incentivizes workers to complete tasks with heightened quality and efficiency. It also provides a timeliness selection mechanism, which makes TsIFedCrowd suitable for both real-time crowdsourcing, where the generation time of task results (data) needs to meet the established requirements of the application, and non-real-time crowdsourcing. TsIFedCrowd mandates clients to complete federated crowdsourcing tasks while maximizing utility for both clients and the server, achieved through Nash equilibrium resolution. TsIFedCrowd is also extended to the multiple heterogeneous federated crowdsourcing scenario. Extensive experiments demonstrate TsIFedCrowd’s effectiveness in ensuring incentive fairness and universality, accelerating convergence speed, and budget savings. Real-world crowdsourcing tasks further validate its efficacy.