Decoding Molecular Graph Embeddings with Reinforcement Learning
Machine Learning
2019-06-06 v2 Machine Learning
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.
Cite
@article{arxiv.1904.08915,
title = {Decoding Molecular Graph Embeddings with Reinforcement Learning},
author = {Steven Kearnes and Li Li and Patrick Riley},
journal= {arXiv preprint arXiv:1904.08915},
year = {2019}
}
Comments
Presented at the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data. Copyright 2019 by the author(s)