Learning Long-Range Representations with Equivariant Messages

TMLR Paper6853 Authors

Abstract:

Machine learning interatomic potentials trained on first-principles reference data are becoming valuable tools for computational physics, biology, and chemistry. Equivariant message-passing neural networks, including transformers, achieve state-of-the-art accuracy but rely on cutoff-based graphs, limiting their ability to capture long-range effects such as electrostatics or dispersion, as well as electron delocalization. While long-range correction schemes based on inverse power laws of interatomic distances have been proposed, they are unable to communicate higher-order geometric information and are thus limited in applicability. To address this shortcoming, we propose the use of equivariant, rather than scalar, charges for long-range interactions, and design a graph neural network architecture, Lorem, around this long-range message passing mechanism. We consider several datasets specifically designed to highlight non-local physical effects, and compare short-range message passing with different receptive fields to invariant and equivariant long-range message passing.
Even though most approaches work for careful dataset-specific choices of their hyperparameters, Lorem works consistently without adjustments, with excellent benchmark performance.

Submission Type: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=pXumH5J8xs

Changes Since Last Submission: We changed the font required for the TMLR submission

Assigned Action Editor: ~Grigorios_Chrysos1

Submission Number: 6853