Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
This addresses the challenge of capturing non-local dependencies in continuous domains for researchers in computational chemistry and materials science, offering a novel approach to improve force field accuracy.
The paper tackled the problem of modeling global atomic interactions in many-body systems like molecular force fields by proposing a geometric attention variant that respects physical symmetries, achieving a method that translates molecular geometry into individual atomic contributions dynamically.
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.