Repository logo
 

Actively Learning what makes a Discrete Sequence Valid

Published version
Peer-reviewed

Type

Conference Object

Change log

Authors

Janz, David 
Westhuizen, Jos van der 
Hernández-Lobato, José Miguel 

Abstract

Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences. As a step towards solving this problem, we propose to learn a deep recurrent validator model. Given a partial sequence, our model learns the probability of that sequence occurring as the beginning of a full valid sequence. Thus this identifies valid versus invalid sequences and crucially it also provides insight about how individual sequence elements influence the validity of discrete objects. To learn this model we propose an approach inspired by seminal work in Bayesian active learning. On a synthetic dataset, we demonstrate the ability of our model to distinguish valid and invalid sequences. We believe this is a key step toward learning generative models that faithfully produce valid discrete objects.

Description

Keywords

stat.ML, stat.ML, cs.LG

Journal Title

Conference Name

International Conference on Learning Representations (ICLR) 2018

Journal ISSN

Volume Title

Publisher

OpenReview