Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918037884502016 |
|---|---|
| author | Fujii, Akihiro Ushiku, Yoshitaka Shimizu, Koji Lu, Anh Khoa Augustin Watanabe, Satoshi |
| author_facet | Fujii, Akihiro Ushiku, Yoshitaka Shimizu, Koji Lu, Anh Khoa Augustin Watanabe, Satoshi |
| contents | Gradient-based methods offer a simple, efficient strategy for materials design by directly optimizing candidates using gradients from pretrained property predictors. However, their use in crystal structure optimization is hindered by two key challenges: handling non-differentiable constraints, such as charge neutrality and structural fidelity, and susceptibility to poor local minima. We revisit and extend the gradient-based methods to address these issues. We propose Simultaneous Multi-property Optimization using Adaptive Crystal Synthesizer (SMOACS), which integrates oxidation-number masks and template-based initialization to enforce non-differentiable constraints, avoid poor local minima, and flexibly incorporate additional constraints without retraining. SMOACS enables multi-property optimization. including exceptional targets such as high-temperature superconductivity, and scales to large crystal systems, both persistent challenges for generative models, even those enhanced with gradient-based guidance from property predictors. In experiments on five target properties and three datasets, SMOACS outperforms generative models and Bayesian optimization methods, successfully designing 135-atom perovskite structures that satisfy multiple property targets and constraints, a task at which the other methods fail entirely. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08562 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets Fujii, Akihiro Ushiku, Yoshitaka Shimizu, Koji Lu, Anh Khoa Augustin Watanabe, Satoshi Materials Science Machine Learning Gradient-based methods offer a simple, efficient strategy for materials design by directly optimizing candidates using gradients from pretrained property predictors. However, their use in crystal structure optimization is hindered by two key challenges: handling non-differentiable constraints, such as charge neutrality and structural fidelity, and susceptibility to poor local minima. We revisit and extend the gradient-based methods to address these issues. We propose Simultaneous Multi-property Optimization using Adaptive Crystal Synthesizer (SMOACS), which integrates oxidation-number masks and template-based initialization to enforce non-differentiable constraints, avoid poor local minima, and flexibly incorporate additional constraints without retraining. SMOACS enables multi-property optimization. including exceptional targets such as high-temperature superconductivity, and scales to large crystal systems, both persistent challenges for generative models, even those enhanced with gradient-based guidance from property predictors. In experiments on five target properties and three datasets, SMOACS outperforms generative models and Bayesian optimization methods, successfully designing 135-atom perovskite structures that satisfy multiple property targets and constraints, a task at which the other methods fail entirely. |
| title | Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2410.08562 |