Crowdsourced PAC Learning under Classification Noise
This work addresses the challenge of learning from noisy crowdsourced data for applications like data labeling, though it appears incremental as it builds on existing PAC learning and crowdsourcing methods.
The paper tackles the problem of PAC learning from crowdsourced labels with classification noise by developing a three-step algorithm that combines majority voting, pure-exploration bandits, and noisy-PAC learning. The result shows improvements over a baseline by reducing the total number of tasks given to workers, with proven guarantees on the number of labeled tasks required.
In this paper, we analyze PAC learnability from labels produced by crowdsourcing. In our setting, unlabeled examples are drawn from a distribution and labels are crowdsourced from workers who operate under classification noise, each with their own noise parameter. We develop an end-to-end crowdsourced PAC learning algorithm that takes unlabeled data points as input and outputs a trained classifier. Our three-step algorithm incorporates majority voting, pure-exploration bandits, and noisy-PAC learning. We prove several guarantees on the number of tasks labeled by workers for PAC learning in this setting and show that our algorithm improves upon the baseline by reducing the total number of tasks given to workers. We demonstrate the robustness of our algorithm by exploring its application to additional realistic crowdsourcing settings.