Entropy-based Active Learning of Graph Neural Network Surrogate Models for Materials Properties

Abstract

Graph neural networks, trained on experimental or calculated data are becoming an increasingly important tool in computational materials science. Networks, once trained, are able to make highly accurate predictions at a fraction of the cost of experiments or first-principles calculations of comparable accuracy. However these networks typically rely on large databases of labelled experiments to train the model. In scenarios where data is scarce or expensive to obtain this can be prohibitive. By building a neural network that provides a confidence on the predicted properties, we are able to develop an active learning scheme that can reduce the amount of labelled data required, by identifying the areas of chemical space where the model is most uncertain. We present a scheme for coupling a graph neural network with a Gaussian process to featurise solid-state materials and predict properties \textit{including} a measure of confidence in the prediction. We then demonstrate that this scheme can be used in an active learning context to speed up the training of the model, by selecting the optimal next experiment for obtaining a data label. Our active learning scheme can double the rate at which the performance of the model on a test data set improves with additional data compared to choosing the next sample at random. This type of uncertainty quantification and active learning has the potential to open up new areas of materials science, where data are scarce and expensive to obtain, to the transformative power of graph neural networks.

References in corpus (19)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Unsupervised Representation Learning by Predicting Image Rotations
• Weight Uncertainty in Neural Networks
• Less is more: sampling chemical space with active learning
• Active learning of linearly parametrized interatomic potentials
• Physics-inspired structural representations for molecules and materials
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Recent Advances in Autoencoder-Based Representation Learning
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Machine-learned multi-system surrogate models for materials prediction
• Efficient global structure optimization with a machine learned surrogate model
• Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
• Transfer learning for materials informatics using crystal graph convolutional neural network
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Modelling the dielectric constants of crystals using machine learning
• Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction