Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

By Tian Xie, Jeffrey C. Grossman. 2017

2,097 citations recorded by the source corpus.

The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 10^{4} data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Subfields: Catalysis, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Catalysis

In Materials Chemistry

Citations in the corpus

Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials (2018, methodology): “Concurrently with the work presented in this paper Xie and Grossman (2018) have also employed neural message passing on graphs based on Voronoi tessellation and K-nearest neighbors, but they do not include a comparison between the methods.”
AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing (2019, background): “…number of real-world applications [8], including electric grid cascading failure analysis [32], prediction of chemical reactivity [33], prediction of synthesized material properties [34], polypharmacy side-effect modeling [35], accurate advertisement in E-commerce [36], and cybersecurity [37].”
Methods for comparing uncertainty quantifications for material property predictions (2019, methodology): “NN: To establish a baseline for predictive accuracy, we re-trained a previously reported Neural Network (NN) [30, 31] on this study’s training set.”
Tackling Climate Change with Machine Learning (2019, methodology): “ML can be a valuable tool for improving AM processes [197].”
A Note on Over-Smoothing for Graph Neural Networks (2020, methodology): “…performance on semi-supervised classiﬁcation, several variants of GNNs have been developed for this task, including Graph-SAGE (Hamilton et al., 2017), GAT (Veli ˇ ckovi ´ c et al., 2017), SGC (Wu et al., 2019), CGCNN (Xie & Grossman, 2018) and GMNN (Qu et al., 2019) to name a few most recent ones.”