Cartesian atomic cluster expansion for machine learning interatomic potentials

B Cheng - npj Computational Materials, 2024 - nature.com
Abstract Machine learning interatomic potentials are revolutionizing large-scale, accurate
atomistic modeling in material science and chemistry. Many potentials use atomic cluster …

Smooth, exact rotational symmetrization for deep learning on point clouds

S Pozdnyakov, M Ceriotti - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Point clouds are versatile representations of 3D objects and have found widespread
application in science and engineering. Many successful deep-learning models have been …

Symmetry-invariant quantum machine learning force fields

INM Le, O Kiss, J Schuhmacher, I Tavernelli… - arxiv preprint arxiv …, 2023 - arxiv.org
Machine learning techniques are essential tools to compute efficient, yet accurate, force
fields for atomistic simulations. This approach has recently been extended to incorporate …

Complete and Efficient Covariants for 3D Point Configurations with Application to Learning Molecular Quantum Properties

H Maennel, OT Unke, KR Müller - arxiv preprint arxiv:2409.02730, 2024 - arxiv.org
When modeling physical properties of molecules with machine learning, it is desirable to
incorporate $ SO (3) $-covariance. While such models based on low body order features are …

A geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure

X Jiang, Z Tian, K Li, W Hu - The Journal of Chemical Physics, 2023 - pubs.aip.org
Modeling the dynamics of glassy systems has been challenging in physics for several
decades. Recent studies have shown the efficacy of Graph Neural Networks (GNNs) in …

Complete and Efficient Covariants for Three-Dimensional Point Configurations with Application to Learning Molecular Quantum Properties

H Maennel, OT Unke, KR Müller - The Journal of Physical …, 2024 - ACS Publications
When physical properties of molecules are being modeled with machine learning, it is
desirable to incorporate SO (3)-covariance. While such models based on low body order …

Capturing short-range order in high-entropy alloys with machine learning potentials

Y Cao, K Sheriff, R Freitas - arxiv preprint arxiv:2401.06622, 2024 - arxiv.org
Chemical short-range order (SRO) affects the distribution of elements throughout the solid-
solution phase of metallic alloys, thereby modifying the background against which …

Mean-field density matrix decompositions

JJ Eriksen - The Journal of Chemical Physics, 2020 - pubs.aip.org
We introduce new and robust decompositions of mean-field Hartree–Fock and Kohn–Sham
density functional theory relying on the use of localized molecular orbitals and physically …

Weisfeiler Leman for Euclidean Equivariant Machine Learning

S Hordan, T Amir, N Dym - arxiv preprint arxiv:2402.02484, 2024 - arxiv.org
The $ k $-Weifeiler-Leman ($ k $-WL) graph isomorphism test hierarchy is a common
method for assessing the expressive power of graph neural networks (GNNs). Recently, the …

Integer linear programming for unsupervised training set selection in molecular machine learning

M Haeberle, P van Gerwen, R Laplaza… - arxiv preprint arxiv …, 2024 - arxiv.org
Integer linear programming (ILP) is an elegant approach to solve linear optimization
problems, naturally described using integer decision variables. Within the context of physics …