Formula graph self-attention network for representation-domain independent materials discovery

Abstract

The success of machine learning (ML) in materials property prediction depends heavily on how the materials are represented for learning. Two dominant families of material descriptors exist, one that encodes crystal structure in the representation and the other that only uses stoichiometric information with the hope of discovering new materials. Graph neural networks (GNNs) in particular have excelled in predicting material properties within chemical accuracy. However, current GNNs are limited to only one of the above two avenues owing to the little overlap between respective material representations. Here, we introduce a new concept of formula graph which unifies stoichiometry-only and structure-based material descriptors. We further develop a self-attention integrated GNN that assimilates a formula graph and show that the proposed architecture produces material embeddings transferable between the two domains. Our model can outperform some previously proposed structure-agnostic models and their structure-based counterparts while exhibiting better sample efficiency and faster convergence. Finally, the model is applied in a challenging exemplar to predict the complex dielectric function of materials and nominate new substances that potentially exhibit epsilon-near-zero phenomena.

References in corpus (26)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Epsilon-Near-Zero Al-Doped ZnO for Ultrafast Switching at Telecom Wavelengths: Outpacing the Traditional Amplitude-Bandwidth Trade-Off
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Insightful classification of crystal structures using deep learning
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• The electronic-structure origin of cation disorder in transition-metal oxides
• Computational screening of high-performance optoelectronic materials using OptB88vdW and TB-mBJ formalisms
• MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
• AtomSets -- A Hierarchical Transfer Learning Framework for Small and Large Materials Datasets
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Direct prediction of phonon density of states with Euclidean neural networks
• High-harmonic generation in metallic titanium nitride
• Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
• Analogical discovery of disordered perovskite oxides by crystal structure information hidden in unsupervised material fingerprints
• Formula graph self-attention network for representation-domain independent materials discovery
• Interactive Human-Machine Learning Framework for Modelling of Ferroelectric-Dielectric Composites

Cited by in corpus (3)

• A critical examination of robustness and generalizability of machine learning prediction of materials properties
• DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
• Formula graph self-attention network for representation-domain independent materials discovery