Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zaverkin, Viktor, Alesiani, Francesco, Maruyama, Takashi, Errica, Federico, Christiansen, Henrik, Takamoto, Makoto, Weber, Nicolas, Niepert, Mathias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912101405032448
author Zaverkin, Viktor
Alesiani, Francesco
Maruyama, Takashi
Errica, Federico
Christiansen, Henrik
Takamoto, Makoto
Weber, Nicolas
Niepert, Mathias
author_facet Zaverkin, Viktor
Alesiani, Francesco
Maruyama, Takashi
Errica, Federico
Christiansen, Henrik
Takamoto, Makoto
Weber, Nicolas
Niepert, Mathias
contents The ability to perform fast and accurate atomistic simulations is crucial for advancing the chemical sciences. By learning from high-quality data, machine-learned interatomic potentials achieve accuracy on par with ab initio and first-principles methods at a fraction of their computational cost. The success of machine-learned interatomic potentials arises from integrating inductive biases such as equivariance to group actions on an atomic system, e.g., equivariance to rotations and reflections. In particular, the field has notably advanced with the emergence of equivariant message passing. Most of these models represent an atomic system using spherical tensors, tensor products of which require complicated numerical coefficients and can be computationally demanding. Cartesian tensors offer a promising alternative, though state-of-the-art methods lack flexibility in message-passing mechanisms, restricting their architectures and expressive power. This work explores higher-rank irreducible Cartesian tensors to address these limitations. We integrate irreducible Cartesian tensor products into message-passing neural networks and prove the equivariance and traceless property of the resulting layers. Through empirical evaluations on various benchmark data sets, we consistently observe on-par or better performance than that of state-of-the-art spherical and Cartesian models.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14253
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Zaverkin, Viktor
Alesiani, Francesco
Maruyama, Takashi
Errica, Federico
Christiansen, Henrik
Takamoto, Makoto
Weber, Nicolas
Niepert, Mathias
Machine Learning
Computational Physics
The ability to perform fast and accurate atomistic simulations is crucial for advancing the chemical sciences. By learning from high-quality data, machine-learned interatomic potentials achieve accuracy on par with ab initio and first-principles methods at a fraction of their computational cost. The success of machine-learned interatomic potentials arises from integrating inductive biases such as equivariance to group actions on an atomic system, e.g., equivariance to rotations and reflections. In particular, the field has notably advanced with the emergence of equivariant message passing. Most of these models represent an atomic system using spherical tensors, tensor products of which require complicated numerical coefficients and can be computationally demanding. Cartesian tensors offer a promising alternative, though state-of-the-art methods lack flexibility in message-passing mechanisms, restricting their architectures and expressive power. This work explores higher-rank irreducible Cartesian tensors to address these limitations. We integrate irreducible Cartesian tensor products into message-passing neural networks and prove the equivariance and traceless property of the resulting layers. Through empirical evaluations on various benchmark data sets, we consistently observe on-par or better performance than that of state-of-the-art spherical and Cartesian models.
title Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2405.14253