Timezone: »
Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels. Existing mechanisms are often developed as one-shot static solutions, assuming a certain level of knowledge about worker models (expertise levels, costs for exerting efforts, etc.). In this paper, we propose a novel inference aided reinforcement mechanism that acquires data sequentially and requires no such prior assumptions. Specifically, we first design a Gibbs sampling augmented Bayesian inference algorithm to estimate workers' labeling strategies from the collected labels at each step. Then we propose a reinforcement incentive learning (RIL) method, building on top of the above estimates, to uncover how workers respond to different payments. RIL dynamically determines the payment without accessing any ground-truth labels. We theoretically prove that RIL is able to incentivize rational workers to provide high-quality labels both at each step and in the long run. Empirical results show that our mechanism performs consistently well under both rational and non-fully rational (adaptive learning) worker models. Besides, the payments offered by RIL are more robust and have lower variances compared to existing one-shot mechanisms.
Author Information
Zehong Hu (Alibaba Group)
Yitao Liang (UCLA)
Jie Zhang (Nanyang Technological University)
Zhao Li (Alibaba Group)
Yang Liu (Harvard University)
More from the Same Authors
-
2021 Spotlight: Learning Large Neighborhood Search Policy for Integer Programming »
Yaoxin Wu · Wen Song · Zhiguang Cao · Jie Zhang -
2022 Poster: Graph Learning Assisted Multi-Objective Integer Programming »
Yaoxin Wu · Wen Song · Zhiguang Cao · Jie Zhang · Abhishek Gupta · Mingyan Lin -
2021 Poster: NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem »
Liang Xin · Wen Song · Zhiguang Cao · Jie Zhang -
2021 Poster: Learning Large Neighborhood Search Policy for Integer Programming »
Yaoxin Wu · Wen Song · Zhiguang Cao · Jie Zhang -
2020 Poster: Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning »
Cong Zhang · Wen Song · Zhiguang Cao · Jie Zhang · Puay Siew Tan · Xu Chi -
2019 Poster: On Tractable Computation of Expected Predictions »
Pasha Khosravi · YooJung Choi · Yitao Liang · Antonio Vergari · Guy Van den Broeck -
2016 Poster: A Bandit Framework for Strategic Regression »
Yang Liu · Yiling Chen