Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials

TL;DR

MLANet is a novel graph neural network framework that achieves high accuracy and computational efficiency in modeling interatomic potentials, enabling stable and large-scale molecular dynamics simulations.

Contribution

Introduces MLANet with a dual-path dynamic attention mechanism and multi-perspective pooling for improved efficiency and stability in MLIPs.

Findings

Maintains competitive accuracy across diverse datasets.

Achieves lower computational cost than mainstream models.

Enables stable long-time molecular dynamics simulations.

Abstract

The core of molecular dynamics simulation fundamentally lies in the interatomic potential. Traditional empirical potentials lack accuracy, while first-principles methods are computationally prohibitive. Machine learning interatomic potentials (MLIPs) promise near-quantum accuracy at linear cost, but existing models still face challenges in efficiency and stability. We presents Machine Learning Advances Neural Network (MLANet), an efficient and robust graph neural network framework. MLANet introduces a dual-path dynamic attention mechanism for geometry-aware message passing and a multi-perspective pooling strategy to construct comprehensive system representations. This design enables highly accurate modeling of atomic environments while achieving exceptional computational efficiency, making high-fidelity simulations more accessible. Tested across a wide range of datasets spanning diverse systems, including organic molecules (e.g., QM7, MD17), periodic inorganic materials (e.g., Li-containing crystals), two-dimensional materials (e.g., bilayer graphene, black phosphorus), surface catalytic reactions (e.g., formate decomposition), and charged systems, MLANet maintains competitive prediction accuracy while its computational cost is markedly lower than mainstream equivariant models, and it enables stable long-time molecular dynamics simulations. MLANet provides an efficient and practical tool for large-scale, high-accuracy atomic simulations.