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

Xiao Jiang; Zean Tian; Kenli Li; Wangyu Hu

doi:10.1063/5.0162463

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

J Chem Phys. 2023 Oct 14;159(14):144504. doi: 10.1063/5.0162463.

Authors

Xiao Jiang¹, Zean Tian¹, Kenli Li¹, Wangyu Hu²

Affiliations

¹ College of Computer Science and Electronic Engineering, Hunan University, Changsha, China.
² College of Materials Science and Engineering, Hunan University, Changsha, China.

PMID: 37830454
DOI: 10.1063/5.0162463

Abstract

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 capturing particle dynamics from the graph structure of glassy systems. However, current GNN methods do not take the dynamic patterns established by neighboring particles explicitly into account. In contrast to these approaches, this paper introduces a novel dynamical parameter termed "smoothness" based on the theory of graph signal processing, which explores the dynamic patterns from a graph perspective. Present graph-based approaches encode structural features without considering smoothness constraints, leading to a weakened correlation between structure and dynamics, particularly on short timescales. To address this limitation, we propose a Geometry-enhanced Graph Neural Network (Geo-GNN) to learn the smoothness of dynamics. Results demonstrate that our method outperforms state-of-the-art baselines in predicting glassy dynamics. Ablation studies validate the effectiveness of each proposed component in capturing smoothness within dynamics. These findings contribute to a deeper understanding of the interplay between glassy dynamics and static structure.