A Deep Learning Approach to Unsupervised Ensemble Learning

TL;DR

This paper introduces a deep learning framework using Restricted Boltzmann Machines and deep neural networks for unsupervised ensemble learning, especially effective when classifiers are not conditionally independent.

Contribution

It establishes the equivalence between Dawid and Skene's model and RBMs, and proposes a DNN approach to handle dependent classifiers, improving performance over existing methods.

Findings

RBM equivalence to Dawid and Skene's model

DNN approach outperforms state-of-the-art methods

Effective in scenarios with classifier dependence

Abstract

We show how deep learning methods can be applied in the context of crowdsourcing and unsupervised ensemble learning. First, we prove that the popular model of Dawid and Skene, which assumes that all classifiers are conditionally independent, is {\em equivalent} to a Restricted Boltzmann Machine (RBM) with a single hidden node. Hence, under this model, the posterior probabilities of the true labels can be instead estimated via a trained RBM. Next, to address the more general case, where classifiers may strongly violate the conditional independence assumption, we propose to apply RBM-based Deep Neural Net (DNN). Experimental results on various simulated and real-world datasets demonstrate that our proposed DNN approach outperforms other state-of-the-art methods, in particular when the data violates the conditional independence assumption.