Variational Bayesian Inference for Crowdsourcing Predictions

TL;DR

This paper introduces a variational Bayesian method for crowdsourcing prediction tasks, effectively modeling worker noise and improving accuracy over traditional methods in both synthetic and real-world datasets.

Contribution

It develops a novel Bayesian framework with variational inference for crowdsourcing function estimation, addressing overfitting and modeling worker noise structures.

Findings

Bayesian methods outperform non-Bayesian approaches in accuracy

Models effectively handle independent and low-rank worker noise

Significant improvements demonstrated on real-world datasets

Abstract

Crowdsourcing has emerged as an effective means for performing a number of machine learning tasks such as annotation and labelling of images and other data sets. In most early settings of crowdsourcing, the task involved classification, that is assigning one of a discrete set of labels to each task. Recently, however, more complex tasks have been attempted including asking crowdsource workers to assign continuous labels, or predictions. In essence, this involves the use of crowdsourcing for function estimation. We are motivated by this problem to drive applications such as collaborative prediction, that is, harnessing the wisdom of the crowd to predict quantities more accurately. To do so, we propose a Bayesian approach aimed specifically at alleviating overfitting, a typical impediment to accurate prediction models in practice. In particular, we develop a variational Bayesian technique for two different worker noise models - one that assumes workers' noises are independent and the other that assumes workers' noises have a latent low-rank structure. Our evaluations on synthetic and real-world datasets demonstrate that these Bayesian approaches perform significantly better than existing non-Bayesian approaches and are thus potentially useful for this class of crowdsourcing problems.