Predicting molecular properties with covariant compositional networks

Abstract

Density functional theory (DFT) is the most successful and widely used approach for computing the electronic structure of matter. However, for tasks involving large sets of candidate molecules, running DFT separately for every possible compound of interest is forbiddingly expensive. In this paper, we propose a neural network based machine learning algorithm which, assuming a sufficiently large training sample of actual DFT results, can instead learn to predict certain properties of molecules purely from their molecular graphs. Our algorithm is based on the recently proposed covariant compositional networks framework and involves tensor reduction operations that are covariant with respect to permutations of the atoms. This new approach avoids some of the representational limitations of other neural networks that are popular in learning from molecular graphs and yields promising results in numerical experiments on the Harvard Clean Energy Project and QM9 molecular datasets.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 27, 2018
Source ID
10.1063/1.5024797

Entities

People

  • Brandon M. Anderson
  • Horace Pan
  • Risi Kondor
  • Shubhendu Trivedi
  • Truong Son Hy

Organizations

  • Defense Advanced Research Projects Agency
  • Toyota Technological Institute
  • University of Chicago

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Quantum Chemistry

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Microelectronics