English

Junction Tree Variational Autoencoder for Molecular Graph Generation

Machine Learning 2019-04-01 v4 Neural and Evolutionary Computing Machine Learning

Abstract

We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings instead of graphs. Our junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network. This approach allows us to incrementally expand molecules while maintaining chemical validity at every step. We evaluate our model on multiple tasks ranging from molecular generation to optimization. Across these tasks, our model outperforms previous state-of-the-art baselines by a significant margin.

Keywords

Cite

@article{arxiv.1802.04364,
  title  = {Junction Tree Variational Autoencoder for Molecular Graph Generation},
  author = {Wengong Jin and Regina Barzilay and Tommi Jaakkola},
  journal= {arXiv preprint arXiv:1802.04364},
  year   = {2019}
}
R2 v1 2026-06-23T00:20:08.059Z