Accurate Prediction of Tensorial Spectra Using Equivariant Graph Neural Network

2025/05/08 by Zhenyao Fang, Hsu, Ting-Wei, Fang, Zhenyao +4 · 1 citation
Computer Science · #Advanced Graph Neural Networks #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci) #Neural Networks and Applications #Neural Networks and Reservoir Computing #Optics (physics.optics)

paper · pdf · doi:10.48550/arxiv.2505.04862

openalex publication_date 2025/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Migrating the models and dataset from Github

Citations

• Database of Tensorial Optical and Transport Properties of Materials From the Wannier Function Method
• Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multi-Output & Multi-Fidelity Machine Learning Approach
• Leveraging Persistent Homology Features for Accurate Defect Formation Energy Predictions via Graph Neural Networks
• Ensemble-Embedding Graph Neural Network for Direct Prediction of Optical Spectra from Crystal Structure
• Equivariant Graph Neural Networks for Prediction of Tensor Material Properties of Crystals
• A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction
• Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential
• Discovery of highly anisotropic dielectric crystals with equivariant graph neural networks
• Towards Accurate Prediction of Configurational Disorder Properties in Materials using Graph Neural Networks
• Probing quantum geometry through optical conductivity and magnetic circular dichroism
• Exploring van der Waals materials with high anisotropy: geometrical and optical approaches
• Predicting Density of States via Multi-modal Transformer
• Virtual Node Graph Neural Network for Full Phonon Prediction
• High-throughput optical absorption spectra for inorganic semiconductors
• e3nn: Euclidean Neural Networks
• E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
• Programmable photonic circuits
• Optuna: A Next-generation Hyperparameter Optimization Framework
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry\n and Semantics
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Maximally localized Wannier functions: Theory and applications
• Electronic excitations: density-functional versus many-body Green’s-function approaches
• Maximally-localized generalized Wannier functions for composite energy bands

Cited by

• A Machine Learning Framework for Modeling Ensemble Properties of Atomically Disordered Materials

Related

• Discovery of highly anisotropic dielectric crystals with equivariant graph neural networks
• Equivariant Graph Neural Networks for Prediction of Tensor Material Properties of Crystals
• Edge-based Tensor prediction via graph neural networks
• Ensemble-Embedding Graph Neural Network for Direct Prediction of Optical Spectra from Crystal Structure
• A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction