Vector Field Oriented Diffusion Model for Crystal Material Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929206395404288 |
|---|---|
| author | Klipfel, Astrid Fregier, Yaël Sayede, Adlane Bouraoui, Zied |
| author_facet | Klipfel, Astrid Fregier, Yaël Sayede, Adlane Bouraoui, Zied |
| contents | Discovering crystal structures with specific chemical properties has become an increasingly important focus in material science. However, current models are limited in their ability to generate new crystal lattices, as they only consider atomic positions or chemical composition. To address this issue, we propose a probabilistic diffusion model that utilizes a geometrically equivariant GNN to consider atomic positions and crystal lattices jointly. To evaluate the effectiveness of our model, we introduce a new generation metric inspired by Frechet Inception Distance, but based on GNN energy prediction rather than InceptionV3 used in computer vision. In addition to commonly used metrics like validity, which assesses the plausibility of a structure, this new metric offers a more comprehensive evaluation of our model's capabilities. Our experiments on existing benchmarks show the significance of our diffusion model. We also show that our method can effectively learn meaningful representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05402 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Vector Field Oriented Diffusion Model for Crystal Material Generation Klipfel, Astrid Fregier, Yaël Sayede, Adlane Bouraoui, Zied Materials Science Artificial Intelligence Machine Learning Discovering crystal structures with specific chemical properties has become an increasingly important focus in material science. However, current models are limited in their ability to generate new crystal lattices, as they only consider atomic positions or chemical composition. To address this issue, we propose a probabilistic diffusion model that utilizes a geometrically equivariant GNN to consider atomic positions and crystal lattices jointly. To evaluate the effectiveness of our model, we introduce a new generation metric inspired by Frechet Inception Distance, but based on GNN energy prediction rather than InceptionV3 used in computer vision. In addition to commonly used metrics like validity, which assesses the plausibility of a structure, this new metric offers a more comprehensive evaluation of our model's capabilities. Our experiments on existing benchmarks show the significance of our diffusion model. We also show that our method can effectively learn meaningful representations. |
| title | Vector Field Oriented Diffusion Model for Crystal Material Generation |
| topic | Materials Science Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.05402 |