Improving Molecular Design by Stochastic Iterative Target Augmentation

Abstract

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain. Finally, we show that our approach is useful in other domains as well, such as program synthesis.

arXiv commentICML 2020

References in corpus (13)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Neural Message Passing for Quantum Chemistry
• Unsupervised Data Augmentation for Consistency Training
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Conditional molecular design with deep generative models
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Grammar Variational Autoencoder
• Understanding Back-Translation at Scale
• Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
• Conditioning by adaptive sampling for robust design
• Design by adaptive sampling
• Hierarchical Graph-to-Graph Translation for Molecules