Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems

06/04/2021
by   Thorben Frank, et al.
0

Attention mechanisms are developing into a viable alternative to convolutional layers as elementary building block of NNs. Their main advantage is that they are not restricted to capture local dependencies in the input, but can draw arbitrary connections. This unprecedented capability coincides with the long-standing problem of modeling global atomic interactions in molecular force fields and other many-body problems. In its original formulation, however, attention is not applicable to the continuous domains in which the atoms live. For this purpose we propose a variant to describe geometric relations for arbitrary atomic configurations in Euclidean space that also respects all relevant physical symmetries. We furthermore demonstrate, how the successive application of our learned attention matrices effectively translates the molecular geometry into a set of individual atomic contributions on-the-fly.

READ FULL TEXT

page 20

page 21

page 22

page 23

page 24

page 25

page 26

page 30

research
06/28/2019

MGOS: A Library for Molecular Geometry and its Operating System

The geometry of atomic arrangement underpins the structural understandin...
research
06/22/2023

Molecular geometric deep learning

Geometric deep learning (GDL) has demonstrated huge power and enormous p...
research
07/16/2022

Distance-Geometric Graph Attention Network (DG-GAT) for 3D Molecular Geometry

Deep learning for molecular science has so far mainly focused on 2D mole...
research
09/25/2019

A Generative Model for Molecular Distance Geometry

Computing equilibrium states for many-body systems, such as molecules, i...
research
08/22/2021

Graph-Convolutional Deep Learning to Identify Optimized Molecular Configurations

Tackling molecular optimization problems using conventional computationa...
research
02/04/2022

Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems

We introduce a multi-tasking graph convolutional neural network, HydraGN...
research
08/25/2023

Physics-inspired Equivariant Descriptors of Non-bonded Interactions

Most of the existing machine-learning schemes applied to atomic-scale si...

Please sign up or login with your details

Forgot password? Click here to reset