RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design

TL;DR

This paper introduces RGCVAE, a novel relational graph variational autoencoder that improves molecule generation by capturing data distribution more effectively and training faster than existing models.

Contribution

RGCVAE combines a new relational graph isomorphism network with a probabilistic decoder, advancing molecule design with improved efficiency and performance.

Findings

Outperforms state-of-the-art VAEs in molecule generation

Faster training times compared to existing methods

Achieves high-quality molecule generation on benchmark datasets

Abstract

Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule generation. Deep Graph Variational Autoencoders are among the most powerful machine learning tools with which it is possible to address this problem. However, existing methods struggle in capturing the true data distribution and tend to be computationally expensive. In this work, we propose RGCVAE, an efficient and effective Graph Variational Autoencoder based on: (i) an encoding network exploiting a new powerful Relational Graph Isomorphism Network; (ii) a novel probabilistic decoding component. Compared to several state-of-the-art VAE methods on two widely adopted datasets, RGCVAE shows state-of-the-art molecule generation performance while being significantly faster to train.