Interpretability of linear regression models of glassy dynamics

Abstract

Data-driven models can accurately describe and predict the dynamical properties of glass-forming liquids from structural data. Accurate predictions, however, do not guarantee an understanding of the underlying physical phenomena and the key factors that control them. In this paper, we illustrate the merits and limitations of linear regression models of glassy dynamics built on high-dimensional structural descriptors. By analyzing data for a two-dimensional glass model, we show that several descriptors commonly used in glass-transition studies display multicollinearity, which hinders the interpretability of linear models. Ridge regression suppresses some of the shortcomings of multicollinearity, but its solutions are not concise enough to be physically interpretable. Only by using dimensional reduction techniques we do eventually obtain linear models that strike a balance between prediction accuracy and interpretability. Our analysis points to a key role of local packing and composition fluctuations in the glass model under study.

25 pages, 23 figures; data and workflow to reproduce the findings of this work are available at https://doi.org/10.5281/zenodo.16942436

References in corpus (36)

• Dynamics of Viscoplastic Deformation in Amorphous Solids
• Theoretical perspective on the glass transition and amorphous materials
• 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
• Vibrational modes identify soft spots in a sheared disordered packing
• Predicting the long time dynamic heterogeneity in a supercooled liquid on the basis of short time heterogeneities
• Predicting plasticity in disordered solids from structural indicators
• Understanding fragility in supercooled Lennard-Jones mixtures. I. Locally preferred structures
• The Monte-Carlo dynamics of a binary Lennard-Jones glass-forming mixture
• Structure and dynamics in glass-formers: predictability at large length scales
• Local yield stress statistics in model amorphous solids
• Unveiling Dimensionality Dependence of Glassy Dynamics: 2D Infinite Fluctuation Eclipses Inherent Structural Relaxation
• Correlation of Local Order with Particle Mobility in Supercooled Liquids is Highly System Dependent
• Information-theoretic measurements of coupling between structure and dynamics in glass-formers
• Plasticity in amorphous solids is mediated by topological defects in the displacement field
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• An introduction to the colloidal glass transition
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Tuning Jammed Frictionless Disk Packings from Isostatic to Hyperstatic
• Topology of vibrational modes predict plastic events in glasses
• Ultrastable metallic glasses in silico
• Non-Equilibrium Phase Transition in an Atomistic Glassformer: the Connection to Thermodynamics
• Relevance of Shear Transformations in the Relaxation of Supercooled Liquids
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Roadmap on machine learning glassy dynamics
• Finding defects in glasses through machine learning
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Identifying structural signature of dynamical heterogeneity via the local softness parameter
• 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
• Classifying the age of a glass based on structural properties: A machine learning approach
• Dead or alive: Distinguishing active from passive particles using supervised learning
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• 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