Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.02407 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911207878819840 |
|---|---|
| author | Kazeev, Nikita Nong, Wei Romanov, Ignat Zhu, Ruiming Ustyuzhanin, Andrey Yamazaki, Shuya Hippalgaonkar, Kedar |
| author_facet | Kazeev, Nikita Nong, Wei Romanov, Ignat Zhu, Ruiming Ustyuzhanin, Andrey Yamazaki, Shuya Hippalgaonkar, Kedar |
| contents | Crystal symmetry plays a fundamental role in determining its physical, chemical, and electronic properties such as electrical and thermal conductivity, optical and polarization behavior, and mechanical strength. Almost all known crystalline materials have internal symmetry. However, this is often inadequately addressed by existing generative models, making the consistent generation of stable and symmetrically valid crystal structures a significant challenge. We introduce WyFormer, a generative model that directly tackles this by formally conditioning on space group symmetry. It achieves this by using Wyckoff positions as the basis for an elegant, compressed, and discrete structure representation. To model the distribution, we develop a permutation-invariant autoregressive model based on the Transformer encoder and an absence of positional encoding. Extensive experimentation demonstrates WyFormer's compelling combination of attributes: it achieves best-in-class symmetry-conditioned generation, incorporates a physics-motivated inductive bias, produces structures with competitive stability, predicts material properties with competitive accuracy even without atomic coordinates, and exhibits unparalleled inference speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02407 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Wyckoff Transformer: Generation of Symmetric Crystals Kazeev, Nikita Nong, Wei Romanov, Ignat Zhu, Ruiming Ustyuzhanin, Andrey Yamazaki, Shuya Hippalgaonkar, Kedar Materials Science Machine Learning Computational Physics I.2.6 Crystal symmetry plays a fundamental role in determining its physical, chemical, and electronic properties such as electrical and thermal conductivity, optical and polarization behavior, and mechanical strength. Almost all known crystalline materials have internal symmetry. However, this is often inadequately addressed by existing generative models, making the consistent generation of stable and symmetrically valid crystal structures a significant challenge. We introduce WyFormer, a generative model that directly tackles this by formally conditioning on space group symmetry. It achieves this by using Wyckoff positions as the basis for an elegant, compressed, and discrete structure representation. To model the distribution, we develop a permutation-invariant autoregressive model based on the Transformer encoder and an absence of positional encoding. Extensive experimentation demonstrates WyFormer's compelling combination of attributes: it achieves best-in-class symmetry-conditioned generation, incorporates a physics-motivated inductive bias, produces structures with competitive stability, predicts material properties with competitive accuracy even without atomic coordinates, and exhibits unparalleled inference speed. |
| title | Wyckoff Transformer: Generation of Symmetric Crystals |
| topic | Materials Science Machine Learning Computational Physics I.2.6 |
| url | https://arxiv.org/abs/2503.02407 |