A Semi-supervised Sensing Rate Learning based CMAB scheme to combat COVID-19 by trustful data collection in the crowd

Jianheng Tang, Kejia Fan, Wenxuan Xie, Luomin Zeng, Feijiang Han, Guosheng Huang, Tian Wang, Anfeng Liu, Shaobo Zhang

Abstract: Highlights•Model the UWR problem as a multi-armed bandit reverse auction problem, and design an UCB-based algorithm to separate the exploration and exploitation.•A Semi-supervised Sensing Rate Learning approach is proposed to quickly and accurately obtain the workers’ SRs.•Design Semi-supervision based Combinatorial Multi-Armed Bandit reverse Auction (SCMABA).•Prove that the SCMABA can achieve truthfulness, individual rationality and computational efficiency in each recruitment round.•Experimental results show the state-of-art performance of SCMABA on revenue and regret.