# Conditional Constrained Graph Variational Autoencoders for Molecule Design

arXiv: https://arxiv.org/abs/2009.00725 · HTML: https://mlsanity.com/paper/2009.00725/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Graph Diffusion Policy Optimization](https://mlsanity.com/paper/2402.16302/) (2024)
- [Conditional β-VAE for De Novo Molecular Generation](https://mlsanity.com/paper/2205.01592/) (2022)
- [RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design](https://mlsanity.com/paper/2305.11699/) (2023)
- [Interpreting Equivariant Representations](https://mlsanity.com/paper/2401.12588/) (2024)
- [An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design](https://mlsanity.com/paper/2110.05478/) (2021)
- [A Deep Learning Approach to the Prediction of Drug Side-Effects on Molecular Graphs](https://mlsanity.com/paper/2211.16871/) (2022)

## Abstract (arXiv)

In recent years, deep generative models for graphs have been used to generate new molecules. These models have produced good results, leading to several proposals in the literature. However, these models may have troubles learning some of the complex laws governing the chemical world. In this work, we explore the usage of the histogram of atom valences to drive the generation of molecules in such models. We present Conditional Constrained Graph Variational Autoencoder (CCGVAE), a model that implements this key-idea in a state-of-the-art model, and shows improved results on several evaluation metrics on two commonly adopted datasets for molecule generation.