Graph Neural Network Force Fields for Spin Dynamics in Metallic Magnets

• URL: http://arxiv.org/abs/2607.28537v1
• Date: Thu, 30 Jul 2026 17:04:56 GMT
• Title: Graph Neural Network Force Fields for Spin Dynamics in Metallic Magnets
• Abstract summary: We introduce a graph neural network (GNN) magnetic force-field framework that learns the effective magnetic energy functional governing itinerant spin dynamics.<n>We benchmark the method on representative metallic magnetic systems exhibiting collinear, noncollinear, and noncoplanar magnetic order.<n>Our results establish graph neural networks as a powerful framework for machine-learned magnetic force fields.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Metallic magnets exhibit complex spin dynamics governed by electronically generated interactions. Predictive simulations of such dynamics typically require repeated solutions of an underlying electronic problem throughout the time evolution, creating a major computational bottleneck. Here we introduce a graph neural network (GNN) magnetic force-field framework that learns the effective magnetic energy functional governing itinerant spin dynamics directly from electronic calculations. Conceptually analogous to machine-learned interatomic potentials, the proposed framework enables efficient evaluation of spin torques while capturing the nonlinear and spatially extended interactions generated by itinerant electrons. We benchmark the method on representative metallic magnetic systems exhibiting collinear, noncollinear, and noncoplanar magnetic order. The learned force fields accurately reproduce electronically generated spin torques and yield nonequilibrium spin dynamics in excellent agreement with direct electronic simulations. Our results establish graph neural networks as a powerful framework for machine-learned magnetic force fields, providing a pathway toward predictive large-scale simulations of nonequilibrium magnetism across multiple length and time scales.

Related papers

• Precision quantum simulation of magnon spectra and interactions [94.30337065819249]
  We show high-precision simulation of both linear and non-linear response functions in a 2D XY spin-1/2 magnet using an analog-digital superconducting processor of up to 97 qubits.<n>Our results reveal stark variations in magnon decay rates across the Brillouin zone, with enhancement near van Hove singularities and suppression for edge-localized modes.
  arXiv  Detail & Related papers  (2026-07-14T22:11:22Z)
• Magnetic HIP-NN for spin dynamics in disordered itinerant magnets [4.626999327112172]
  We present a magnetic extension of the Hierarchically Interacting Particle Neural Network (HIP-NN)<n>The resulting magnetic HIP-NN incorporates rotationally invariant spin correlations directly into hierarchical message-passing layers.<n>We show that mHIP-NN accurately reproduces the local torques governing Landau-Lifshitz-Gilbert dynamics and faithfully captures the nonequilibrium evolution of spatial spin correlations following thermal quenches.
  arXiv  Detail & Related papers  (2026-06-09T02:57:37Z)
• Machine-learning force-field models for dynamical simulations of metallic magnets [3.1567633240529616]
  We review recent advances in machine learning (ML) force-field methods for Landau-Lifshitz-Gilbert (LLG) simulations of itinerant electron magnets.<n>A deep neural network model is developed to efficiently and accurately predict the electron-mediated forces governing spin dynamics.<n>Results establish ML force-field frameworks as scalable, accurate, and versatile tools for modeling nonequilibrium spin dynamics in itinerant magnets.
  arXiv  Detail & Related papers  (2026-02-20T13:51:29Z)
• Machine learning nonequilibrium phase transitions in charge-density wave insulators [3.4485371511969003]
  We develop a machine learning framework for adiabatic lattice dynamics coupled to nonequilibrium electrons.<n>Our results establish direct force learning as an efficient and accurate approach for simulating nonequilibrium lattice dynamics in driven quantum materials.
  arXiv  Detail & Related papers  (2026-01-12T14:34:50Z)
• Machine learning force-field models for metallic spin glass [4.090038845129619]
  We present a scalable machine learning framework for dynamical simulations of metallic spin glasses. A Behler-Parrinello type neural-network model is developed to accurately and efficiently predict electron-induced local magnetic fields.
  arXiv  Detail & Related papers  (2023-11-28T17:12:03Z)
• Probing dynamics of a two-dimensional dipolar spin ensemble using single qubit sensor [62.997667081978825]
  We experimentally investigate individual spin dynamics in a two-dimensional ensemble of electron spins on the surface of a diamond crystal. We show that this anomalously slow relaxation rate is due to the presence of strong dynamical disorder. Our work paves the way towards microscopic study and control of quantum thermalization in strongly interacting disordered spin ensembles.
  arXiv  Detail & Related papers  (2022-07-21T18:00:17Z)
• Spin-Dependent Graph Neural Network Potential for Magnetic Materials [5.775111970429336]
  SpinGNN is a spin-dependent interatomic potential approach that employs the graph neural network (GNN) to describe magnetic systems. The effectiveness of SpinGNN is demonstrated by its exceptional precision in fitting a high-order spin Hamiltonian and two complex spin-lattice Hamiltonians.
  arXiv  Detail & Related papers  (2022-03-06T01:54:50Z)
• Demonstration of electron-nuclear decoupling at a spin clock transition [54.088309058031705]
  Clock transitions protect molecular spin qubits from magnetic noise. linear coupling to nuclear degrees of freedom causes a modulation and decay of electronic coherence. An absence of quantum information leakage to the nuclear bath provides opportunities to characterize other decoherence sources.
  arXiv  Detail & Related papers  (2021-06-09T16:23:47Z)
• Controlled coherent dynamics of [VO(TPP)], a prototype molecular nuclear qudit with an electronic ancilla [50.002949299918136]
  We show that [VO(TPP)] (vanadyl tetraphenylporphyrinate) is a promising system suitable to implement quantum computation algorithms. It embeds an electronic spin 1/2 coupled through hyperfine interaction to a nuclear spin 7/2, both characterized by remarkable coherence.
  arXiv  Detail & Related papers  (2021-03-15T21:38:41Z)
• Effects of the dynamical magnetization state on spin transfer [68.8204255655161]
  We show that the complex interactions between the spin-polarized electrons and the dynamical states of the local spins can be decomposed into separate processes. Our results suggest that exquisite control of spin transfer efficiency and of the resulting dynamical magnetization states may be achievable.
  arXiv  Detail & Related papers  (2021-01-21T22:12:03Z)
• Energy and momentum conservation in spin transfer [77.34726150561087]
  We show that energy and linear momentum conservation laws impose strong constraints on the properties of magnetic excitations induced by spin transfer. Our results suggest the possibility to achieve precise control of spin transfer-driven magnetization dynamics.
  arXiv  Detail & Related papers  (2020-04-04T15:43:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.