Exploiting Unlabeled Data to Enhance Ensemble Diversity

TL;DR

This paper introduces UDEED, a semi-supervised ensemble method that leverages unlabeled data to enhance diversity among base learners, leading to improved ensemble performance.

Contribution

It proposes a novel approach that maximizes diversity on unlabeled data while maintaining accuracy on labeled data, differing from traditional pseudo-labeling methods.

Findings

UDEED effectively utilizes unlabeled data to improve ensemble diversity.

UDEED outperforms several existing semi-supervised ensemble methods.

Experimental results demonstrate competitive accuracy and diversity enhancement.

Abstract

Ensemble learning aims to improve generalization ability by using multiple base learners. It is well-known that to construct a good ensemble, the base learners should be accurate as well as diverse. In this paper, unlabeled data is exploited to facilitate ensemble learning by helping augment the diversity among the base learners. Specifically, a semi-supervised ensemble method named UDEED is proposed. Unlike existing semi-supervised ensemble methods where error-prone pseudo-labels are estimated for unlabeled data to enlarge the labeled data to improve accuracy, UDEED works by maximizing accuracies of base learners on labeled data while maximizing diversity among them on unlabeled data. Experiments show that UDEED can effectively utilize unlabeled data for ensemble learning and is highly competitive to well-established semi-supervised ensemble methods.