MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leonardi, Francesco, Bonev, Boris, Riesen, Kaspar
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911417682100224
author Leonardi, Francesco
Bonev, Boris
Riesen, Kaspar
author_facet Leonardi, Francesco
Bonev, Boris
Riesen, Kaspar
contents Machine learning force fields (MLFFs) have become essential for accurate and efficient atomistic modeling. Despite their high accuracy, most existing approaches rely on fixed angular expansions, limiting flexibility in weighting local geometric interactions. We introduce Modular Angular-Radial Attention (MARA), a module that extends spherical attention -- originally developed for SO(3) tasks -- to the molecular domain and SE(3), providing an efficient approximation of equivariant interactions. MARA operates directly on the angular and radial coordinates of neighboring atoms, enabling flexible, geometrically informed, and modular weighting of local environments. Unlike existing attention mechanisms in SE(3)-equivariant architectures, MARA can be integrated in a plug-and-play manner into models such as MACE without architectural modifications. Across molecular benchmarks, MARA improves energy and force predictions, reduces high-error events, and enhances robustness. These results demonstrate that continuous spherical attention is an effective and generalizable geometric operator that increases the expressiveness, stability, and reliability of atomistic models.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02671
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fields
Leonardi, Francesco
Bonev, Boris
Riesen, Kaspar
Machine Learning
Artificial Intelligence
Machine learning force fields (MLFFs) have become essential for accurate and efficient atomistic modeling. Despite their high accuracy, most existing approaches rely on fixed angular expansions, limiting flexibility in weighting local geometric interactions. We introduce Modular Angular-Radial Attention (MARA), a module that extends spherical attention -- originally developed for SO(3) tasks -- to the molecular domain and SE(3), providing an efficient approximation of equivariant interactions. MARA operates directly on the angular and radial coordinates of neighboring atoms, enabling flexible, geometrically informed, and modular weighting of local environments. Unlike existing attention mechanisms in SE(3)-equivariant architectures, MARA can be integrated in a plug-and-play manner into models such as MACE without architectural modifications. Across molecular benchmarks, MARA improves energy and force predictions, reduces high-error events, and enhances robustness. These results demonstrate that continuous spherical attention is an effective and generalizable geometric operator that increases the expressiveness, stability, and reliability of atomistic models.
title MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fields
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.02671