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

Abstract

Understanding the dynamic processes of the glassy system continues to be challenging. Recent advances have shown the power of graph neural networks (GNNs) for determining the correlation between structure and dynamics in the glassy system. These methods treat the glassy system as a topological graph. However, the inherent "smoothness" property of the dynamics on the graph (variation of dynamics over the graph) is ignored, resulting in a deteriorated performance of GNN for dynamic predictions over various time scales. In this paper, we first present an experimental investigation assessing the smoothness patterns of particle dynamics from the graph perspective. The results indicate that the long-time dynamics exhibit a smoother property on the graph, while the short-time dynamics reveal a distinctly non-smooth pattern. To establish the relationship between the static structure and dynamics with different smoothness patterns, we propose a novel geometry-enhanced graph neural network (Geo-GNN) model. The Geo-GNN architecture consists of a geometry feature encoder that incorporates rotation-invariant distances and angles to enhance geometric feature learning and a geometry-enhanced aggregation block that can adaptively learn the underlying smoothness patterns during message passing. Experimental results demonstrate that our method is able to capture the inherent smoothness pattern of particles and outperforms state-of-the-art baselines in predicting the dynamics across all time scales. A subsequent study has revealed that geometric features are critical for the model to accurately capture smoothness patterns in dynamics. Our research not only refines the method for predicting glassy dynamics but also provides a new lens through which to investigate the issue of causality regarding dynamical heterogeneity in glasses.

References in corpus (19)

• Theoretical perspective on the glass transition and amorphous materials
• Simplifying Graph Convolutional Networks
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Identifying structural flow defects in disordered solids using machine learning methods
• Roles of icosahedral and crystal-like order in hard spheres glass transition
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Identification of long-lived clusters and their link to slow dynamics in a model glass former
• Calorimetric glass transition explained by hierarchical dynamic facilitation
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Inverse design of glass structure with deep graph neural networks
• Comparing machine learning techniques for predicting glassy dynamics
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Dimensionality reduction of local structure in glassy binary mixtures
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Unsupervised Graph Neural Network Reveals the Structure--Dynamics Correlation in Disordered Systems
• What Do Deep Neural Networks Find in Disordered Structures of Glasses?

Cited by in corpus (6)

• Roadmap on machine learning glassy dynamics
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Machine learning that predicts well may not learn the correct physical descriptions of glassy systems
• Interpretability of linear regression models of glassy dynamics