On Deep Unsupervised Active Learning

TL;DR

This paper introduces DUAL, a deep neural network framework for unsupervised active learning that effectively models data nonlinearity and selects representative samples by preserving data structure in a learned latent space.

Contribution

The paper proposes a novel deep learning approach for unsupervised active learning that explicitly captures nonlinearity and data structure for better sample selection.

Findings

DUAL outperforms existing methods on six datasets.

The framework effectively preserves cluster structures.

Nonlinear embedding improves sample representativeness.

Abstract

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of certain selected samples, and then take these selected samples as representative ones to label. However, in practice, the data do not necessarily conform to linear models, and how to model nonlinearity of data often becomes the key point to success. In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning, called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. In the selection block, DUAL considers to simultaneously preserve the whole input patterns as well as the cluster structure of data. Extensive experiments are performed on six publicly available datasets, and experimental results clearly demonstrate the efficacy of our method, compared with state-of-the-arts.