Crystal Diffusion Variational Autoencoder for Periodic Material Generation
By Tian Xie, Xiang Fu, Octavian-Eugen Ganea, Regina Barzilay, Tommi S. Jaakkola. International Conference on Learning Representations, 2021
444 citations recorded by the source corpus.
Generating the periodic structure of stable materials is a long-standing challenge for the material design community. This task is difficult because stable materials only exist in a low-dimensional subspace of all possible periodic arrangements of atoms: 1) the coordinates must lie in the local energy minimum defined by quantum mechanics, and 2) global stability also requires the structure to follow the complex, yet specific bonding preferences between different atom types. Existing methods fail to incorporate these factors and often lack proper invariances. We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates materials in a diffusion process that moves atomic coordinates towards a lower energy state and updates atom types to satisfy bonding preferences between neighbors. Our model also explicitly encodes interactions across periodic boundaries and respects permutation, translation, rotation, and periodic invariances. We significantly outperform past methods in three tasks: 1) reconstructing the input structure, 2) generating valid, diverse, and realistic materials, and 3) generating materials that optimize a specific property. We also provide several standard datasets and evaluation metrics for the broader machine learning community.
Subfields: Biomedical Engineering, Materials Chemistry
View Paper: https://www.semanticscholar.org/paper/f50f877b07d64f116de7bf161cf009d2ebad7d15
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
In Materials Chemistry
Citations in the corpus
- Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, methodology): “After surpassing GAN on image synthesis [50, 82, 200], diffusion model has shown great potential in numerous tasks, such as computer vision [14, 126, 252], natural language processing [9], temporal data modeling [32, 116, 174, 208], multi-modal modeling [10, 182, 265], robust learning [21, 107, 219]”
- A generative model for inorganic materials design (2025, unknown): “These broad conditioning abilities combined with the improvements in the diffusion process over previous work 4,12 are key for addressing a wide range of inverse design problems (Supplementary Information section A.11).”
- Training Diffusion Models with Reinforcement Learning (2023, unknown): “…in applications including image and video synthesis (Ramesh et al., 2021; Saharia et al., 2022; Ho et al., 2022), drug and material design (Xu et al., 2021; Xie et al., 2021; Schneuing et al., 2022), and continuous control (Janner et al., 2022; Wang et al., 2022; Hansen-Estruch et al., 2023).”