Equivariant Diffusion for Crystal Structure Prediction
By: Peijia Lin , Pin Chen , Rui Jiao and more
Potential Business Impact:
Finds new crystal structures faster and better.
In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process.
Similar Papers
Equivariant Hypergraph Diffusion for Crystal Structure Prediction
Computational Engineering, Finance, and Science
Finds new materials by understanding atom connections.
Physics-informed diffusion models for extrapolating crystal structures beyond known motifs
Materials Science
Finds new building blocks for materials.
ContinuouSP: Generative Model for Crystal Structure Prediction with Invariance and Continuity
Machine Learning (CS)
Finds new materials by predicting crystal shapes.