Exploratory Learning

TL;DR

This paper introduces an exploratory extension of EM for semi-supervised multiclass learning that adapts to unknown class counts, significantly improving F1 scores on multiple datasets.

Contribution

It proposes a novel exploratory EM algorithm that handles unknown class numbers in semi-supervised learning, outperforming existing non-parametric Bayesian methods.

Findings

Improved F1 scores on three datasets.

Outperforms non-parametric Bayesian clustering.

Robustness to unknown class counts.

Abstract

In multiclass semi-supervised learning (SSL), it is sometimes the case that the number of classes present in the data is not known, and hence no labeled examples are provided for some classes. In this paper we present variants of well-known semi-supervised multiclass learning methods that are robust when the data contains an unknown number of classes. In particular, we present an "exploratory" extension of expectation-maximization (EM) that explores different numbers of classes while learning. "Exploratory" SSL greatly improves performance on three datasets in terms of F1 on the classes with seed examples i.e., the classes which are expected to be in the data. Our Exploratory EM algorithm also outperforms a SSL method based non-parametric Bayesian clustering.