Decoding Molecular Graph Embeddings with Reinforcement Learning

2019/04/18 by Steven Kearnes, Li Li, Kearnes, Steven +3 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · Mathematics · #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Protein Structure and Dynamics #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1904.08915

Presented at the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data. Copyright 2019 by the author(s)

openalex publication_date 2019/04/18 · arxiv created 2019/06/04 · arxiv updated 2019/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluation (such as requiring parallel encoders and decoders or non-trivial graph matching). Here, we repurpose a simple graph generator to enable efficient decoding and generation of molecular graphs.

Citations

• Robust Estimation of a Location Parameter
• Tutorial on Variational Autoencoders
• Syntax-Directed Variational Autoencoder for Structured Data
• Junction Tree Variational Autoencoder for Molecular Graph Generation

Cited by

• Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
• Deep learning for molecular design - a review of the state of the art
• Scalable variational Monte Carlo with graph neural ansatz
• Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks

Related

• Auto-encoding Molecules: Graph-Matching Capabilities Matter
• NeVAE: A Deep Generative Model for Molecular Graphs
• Constrained Graph Variational Autoencoders for Molecule Design
• Graph Deconvolutional Generation
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders