On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909379637280768 |
|---|---|
| author | Avilov, Fedor S. Eremin, Roman A. Budennyy, Semen A. Humonen, Innokentiy S. |
| author_facet | Avilov, Fedor S. Eremin, Roman A. Budennyy, Semen A. Humonen, Innokentiy S. |
| contents | Despite an artificial intelligence-assisted modeling of disordered crystals is a widely used and well-tried method of new materials design, the issues of its robustness, reliability, and stability are still not resolved and even not discussed enough. To highlight it, in this work we composed a series of nested intermetallic approximants of quasicrystals datasets and trained various machine learning models on them correspondingly. Our qualitative and, what is more important, quantitative assessment of the difference in the predictions clearly shows that different reasonable changes in the training sample can lead to the completely different set of the predicted potentially new materials. We also showed the advantage of pre-training and proposed a simple yet effective trick of sequential training to increase stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13873 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants Avilov, Fedor S. Eremin, Roman A. Budennyy, Semen A. Humonen, Innokentiy S. Computational Physics Materials Science Machine Learning Despite an artificial intelligence-assisted modeling of disordered crystals is a widely used and well-tried method of new materials design, the issues of its robustness, reliability, and stability are still not resolved and even not discussed enough. To highlight it, in this work we composed a series of nested intermetallic approximants of quasicrystals datasets and trained various machine learning models on them correspondingly. Our qualitative and, what is more important, quantitative assessment of the difference in the predictions clearly shows that different reasonable changes in the training sample can lead to the completely different set of the predicted potentially new materials. We also showed the advantage of pre-training and proposed a simple yet effective trick of sequential training to increase stability. |
| title | On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants |
| topic | Computational Physics Materials Science Machine Learning |
| url | https://arxiv.org/abs/2410.13873 |