A Non Linear Spectral Graph Neural Network Simulator for More Stable and Accurate Rollouts

TL;DR

This paper introduces a nonlinear spectral graph neural network simulator that enhances the stability and accuracy of molecular dynamics rollouts by better capturing long-range interactions and global modes.

Contribution

It proposes a nonlinear spectral GNN architecture that explicitly models global eigenmodes, significantly improving simulation accuracy over existing methods.

Findings

Nonlinear spectral models outperform linear and spatial GNNs.

They better capture slow, global modes in disordered elastic networks.

Results show reduced particle-position errors and improved property predictions.

Abstract

Molecular dynamics (MD) simulations are a central tool in science and engineering enabling the study of dynamical behavior and the link between microscopic structure and macroscopic function. Their high computational cost, however, has motivated extensive efforts to develop accelerated alternatives. A promising approach is the use of machine-learning-based simulators that allow for substantially larger time steps than conventional MD. Among these, graph neural network (GNN)-based methods have been found to be especially attractive given that they naturally encode the inductive bias of interacting particle systems, however current architectures remain limited in accuracy and stability. In particular, standard message-passing schemes struggle to efficiently propagate long-range information. Here, we investigate whether spectral-GNN simulators can overcome these limitations by explicitly representing a simulated system in a global eigenmode basis, and therefore better capture long-range and collective behavior. Focusing on disordered elastic networks, model systems for complex materials and biological structures such as proteins, we compare spatial, linear spectral, and nonlinear spectral GNN architectures. We find that while spectral representations alone are not sufficient, nonlinear spectral models substantially outperform alternatives. By learning both the time-dependent dynamics and the mixing of eigenmodes, these models more accurately capture the system's slow, global modes, which dominate macroscopic behavior. This leads to a marked reduction in systematic particle-position error and significantly improved prediction of global physical properties.