Learning Long-Range Representations with Equivariant Messages

ICLR 2026 Conference Submission17288 Authors

Keywords: Machine learning interatomic potentials, Graph neural networks, Equivariance, Long-range interactions

TL;DR: LOREM is a neural network architecture that uses equivariant long-range message passing to capture non-local physical effects in atomistic simulations

Abstract:

Machine learning interatomic potentials trained on first-principles reference data are quickly becoming indispensable 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 and transferability.
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.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 17288