Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism

Abstract

Glass-forming liquids exhibit slow dynamics below their melting temperatures, maintaining an amorphous structure reminiscent of normal liquids. Distinguishing microscopic structures in the supercooled and high-temperature regimes remains a debated topic. Building on recent advances in machine learning, particularly Graph Neural Networks (GNNs), our study automatically extracts features, unveiling fundamental mechanisms driving structural changes at varying temperatures. We employ the self-attention mechanism to generate attention coefficients that quantify the importance of connections between graph nodes, providing insights into the rationale behind GNN predictions. Exploring structural changes with decreasing temperature through the GNN+self-attention using physically-defined structural descriptors, including the bond-orientational order parameter, Voronoi cell volume, and coordination number, we identify strong correlations between high attention coefficients and more disordered structures as a key indicator of variations in glass-forming liquids.

9pages, 5 figures for main text, 12 pages for Supplementary Material

References in corpus (41)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Comprehensive Survey on Graph Neural Networks
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• Theoretical perspective on the glass transition and amorphous materials
• Accurate determination of crystal structures based on averaged local bond order parameters
• The role of local structure in dynamical arrest
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Identifying structural flow defects in disordered solids using machine learning methods
• Hierarchical structures of amorphous solids characterized by persistent homology
• Bond orientational ordering in liquids: Towards a unified description of water-like anomalies, liquid-liquid transition, glass transition, and crystallization
• Shortcomings of the Bond Orientational Order Parameters for the Analysis of Disordered Particulate Matter
• Predicting the long time dynamic heterogeneity in a supercooled liquid on the basis of short time heterogeneities
• What do we learn from the local geometry of glass-forming liquids?
• Predicting plasticity in disordered solids from structural indicators
• Understanding fragility in supercooled Lennard-Jones mixtures. I. Locally preferred structures
• Autonomously revealing hidden local structures in supercooled liquids
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Unsupervised learning for local structure detection in colloidal systems
• Machine learning determination of atomic dynamics at grain boundaries
• Disconnecting structure and dynamics in glassy thin films
• Multiple length and time scales of dynamic heterogeneities in model glass-forming liquids: A systematic analysis of multi-point and multi-time correlations
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Assessing the structural heterogeneity of supercooled liquids through community inference
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Inverse design of glass structure with deep graph neural networks
• Attractive versus truncated repulsive supercooled liquids: The dynamics is encoded in the pair correlation function
• Roadmap on machine learning 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
• Finding defects in glasses through machine learning
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Roles of liquid structural ordering in glass transition, crystallization, and water's anomalies
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• Exploring glassy dynamics with Markov state models from graph dynamical neural networks
• Classifying the age of a glass based on structural properties: A machine learning approach
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Machine learning glass caging order parameters with an artificial nested neural network
• Automated characterization of spatial and dynamical heterogeneity in supercooled liquids via implementation of Machine Learning
• Towards interpreting the thermally activated $\beta$ dynamics in metallic glass with the structural constraint neural network

Cited by in corpus (2)

• Machine learning evaluation of structural descriptors for supercooled water
• Interpretability of linear regression models of glassy dynamics