Actively Learning what makes a Discrete Sequence Valid

By David Janz, Jos van der Westhuizen, José Miguel Hernández-Lobato. 2017

22 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Junction Tree Variational Autoencoder for Molecular Graph Generation (2018, neutral): “Other techniques such as active learning (Janz et al., 2017) and reinforcement learning (Guimaraes et al.”
Syntax-Directed Variational Autoencoder for Structured Data (2018, background): “Techniques including data augmentation (Bjerrum, 2017), active learning (Janz et al., 2017) and reinforcement learning (Guimaraes et al., 2017) also been proposed to tackle this issue.”
Constrained Bayesian Optimization for Automatic Chemical Design (2017, background): “Although there have been many attempts to address the issue of generating valid molecules, they all rely on model assumptions that can negatively impact either the complexity [Jaques et al., 2017, Janz et al., 2017, Kusner et al., 2017] or the diversity [Jin et al., 2018] of the generated molecules.”
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning (2019, background): “There are a number of intuitive choices, such as model uncertainty and mutual information, and, in this paper, we focus on BALD [19], which has proven itself in the context of deep learning [13, 30, 20].”
A Survey of Deep Active Learning (2020, methodology): “For example, [71, 103] adopts the method of batch acquisition and chooses Bayesian Active Learning by Disagreement (BALD) [97] to query top-K samples with the highest scores.”