Online Task Scheduling With Workers Variabilities in Crowdsourcing

Abstract

Crowdsourcing system, which utilizes many workers to process computer-complexity tasks, has become an effective platform in today’s online labor markets. In a crowdsourcing system, maximizing the total utility is one key design goal. This goal is extremely hard because a computer-complexity task can be a multi-dimensional large-scale task that contains thousands or millions of atomic tasks. In online situation, we need to consider both the varying service of workers and future unknown task arrivals. As we know, none of the previous work considers a multi-dimensional large-scale task assignment for utility maximization. In this paper, an online framework is proposed to solve this optimization problem by running atomic tasks in parallel on workers. To estimate worker service rates, we consider each varying worker as an arm for a multi-armed bandit in crowdsourcing system. We design the online scheduling algorithm from a bandit perspective by Online Convex Optimization (OCO) techniques. We prove that our designed algorithm can yield a sublinear regret bound. Finally, we show that our designed algorithm is better than the baseline algorithms by nearly 10% for the total utility achieved.