Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction

Abstract

Machine learning (ML) methods have gained increasing popularity in exploring and developing new materials. More specifically, graph neural network (GNN) has been applied in predicting material properties. In this work, we develop a novel model, GATGNN, for predicting inorganic material properties based on graph neural networks composed of multiple graph-attention layers (GAT) and a global attention layer. Through the application of the GAT layers, our model can efficiently learn the complex bonds shared among the atoms within each atom's local neighborhood. Subsequently, the global attention layer provides the weight coefficients of each atom in the inorganic crystal material which are used to considerably improve our model's performance. Notably, with the development of our GATGNN model, we show that our method is able to both outperform the previous models' predictions and provide insight into the crystallization of the material.

arXiv comment11 pages. 5 figures

References in corpus (8)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Self-Attention Generative Adversarial Networks
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Fast Graph Representation Learning with PyTorch Geometric
• Talking-Heads Attention

Cited by in corpus (22)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Piezoelectric modulus prediction using machine learning and graph neural networks
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO
• Formula graph self-attention network for representation-domain independent materials discovery
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
• Crystalline Material Discovery in the Era of Artificial Intelligence
• Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• PINK: physical-informed machine learning for lattice thermal conductivity
• Coarse-grained crystal graph neural networks for reticular materials design
• Distance Matrix based Crystal Structure Prediction using Evolutionary Algorithms
• EOSnet: Embedded Overlap Structures for Graph Neural Networks in Predicting Material Properties
• Molecular distance matrix prediction based on graph convolutional networks
• Active learning based generative design for the discovery of wide bandgap materials
• Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
• CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning
• Machine learning-driven elasticity prediction in advanced inorganic materials via convolutional neural networks