Comparing machine learning techniques for predicting glassy dynamics

Abstract

In the quest to understand how structure and dynamics are connected in glasses, a number of machine learning based methods have been developed that predict dynamics in supercooled liquids. These methods include both increasingly complex machine learning techniques, and increasingly sophisticated descriptors used to describe the environment around particles. In many cases, both the chosen machine learning technique and choice of structural descriptors are varied simultaneously, making it hard to quantitatively compare the performance of different machine learning approaches. Here, we use three different machine learning algorithms -- linear regression, neural networks, and GNNs -- to predict the dynamic propensity of a glassy binary hard-sphere mixture using as structural input a recursive set of order parameters recently introduced by Boattini et al. [Phys. Rev. Lett. 127, 088007 (2021)]. As we show, when these advanced descriptors are used, all three methods predict the dynamics with nearly equal accuracy. However, the linear regression is orders of magnitude faster to train making it by far the method of choice.

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Theoretical perspective on the glass transition and amorphous materials
• Accurate determination of crystal structures based on averaged local bond order parameters
• Interaction Networks for Learning about Objects, Relations and Physics
• The role of local structure in dynamical arrest
• Identifying structural flow defects in disordered solids using machine learning methods
• Averaging local structure to predict the dynamic propensity in supercooled liquids

Cited by in corpus (6)

• Modern computational studies of the glass transition
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Discovering dynamic laws from observations: the case of self-propelled, interacting colloids
• Computer simulations of the glass transition and glassy materials
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure