Learning Invariant Representations of Molecules for Atomization Energy Prediction
Abstract
The accurate prediction of molecular energetics in chemical compound space is a crucial ingredient for rational compound design. The inherently graph-like, non-vectorial nature of molecular data gives rise to a unique and difficult machine learning problem. In this paper, we adopt a learning-from-scratch approach where quantum-mechanical molecular energies are predicted directly from the raw molecular geometry. The study suggests a benefit from setting flexible priors and enforcing invariance stochastically rather than structurally. Our results improve the state-of-the-art by a factor of almost three, bringing statistical methods one step closer to the holy grail of ''chemical accuracy''.
Cite
Text
Montavon et al. "Learning Invariant Representations of Molecules for Atomization Energy Prediction." Neural Information Processing Systems, 2012.Markdown
[Montavon et al. "Learning Invariant Representations of Molecules for Atomization Energy Prediction." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/montavon2012neurips-learning/)BibTeX
@inproceedings{montavon2012neurips-learning,
title = {{Learning Invariant Representations of Molecules for Atomization Energy Prediction}},
author = {Montavon, Grégoire and Hansen, Katja and Fazli, Siamac and Rupp, Matthias and Biegler, Franziska and Ziehe, Andreas and Tkatchenko, Alexandre and Lilienfeld, Anatole V. and Müller, Klaus-Robert},
booktitle = {Neural Information Processing Systems},
year = {2012},
pages = {440-448},
url = {https://mlanthology.org/neurips/2012/montavon2012neurips-learning/}
}