Actively Learning what makes a Discrete Sequence Valid

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.

6 pages, 2 figures

References in corpus (7)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Bayesian Active Learning for Classification and Preference Learning
• Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
• Bayesian Recurrent Neural Networks
• Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space

Cited by in corpus (5)

• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Deep learning for molecular design - a review of the state of the art
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• Syntax-Directed Variational Autoencoder for Structured Data
• Constrained Bayesian Optimization for Automatic Chemical Design