Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913684943536128 |
|---|---|
| author | Segal, Nofit Netanyahu, Aviv Greenman, Kevin P. Agrawal, Pulkit Gomez-Bombarelli, Rafael |
| author_facet | Segal, Nofit Netanyahu, Aviv Greenman, Kevin P. Agrawal, Pulkit Gomez-Bombarelli, Rafael |
| contents | Discovery of high-performance materials and molecules requires identifying extremes with property values that fall outside the known distribution. Therefore, the ability to extrapolate to out-of-distribution (OOD) property values is critical for both solid-state materials and molecular design. Our objective is to train predictor models that extrapolate zero-shot to higher ranges than in the training data, given the chemical compositions of solids or molecular graphs and their property values. We propose using a transductive approach to OOD property prediction, achieving improvements in prediction accuracy. In particular, the True Positive Rate (TPR) of OOD classification of materials and molecules improved by 3x and 2.5x, respectively, and precision improved by 2x and 1.5x compared to non-transductive baselines. Our method leverages analogical input-target relations in the training and test sets, enabling generalization beyond the training target support, and can be applied to any other material and molecular tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules Segal, Nofit Netanyahu, Aviv Greenman, Kevin P. Agrawal, Pulkit Gomez-Bombarelli, Rafael Machine Learning Materials Science Computational Engineering, Finance, and Science Chemical Physics Discovery of high-performance materials and molecules requires identifying extremes with property values that fall outside the known distribution. Therefore, the ability to extrapolate to out-of-distribution (OOD) property values is critical for both solid-state materials and molecular design. Our objective is to train predictor models that extrapolate zero-shot to higher ranges than in the training data, given the chemical compositions of solids or molecular graphs and their property values. We propose using a transductive approach to OOD property prediction, achieving improvements in prediction accuracy. In particular, the True Positive Rate (TPR) of OOD classification of materials and molecules improved by 3x and 2.5x, respectively, and precision improved by 2x and 1.5x compared to non-transductive baselines. Our method leverages analogical input-target relations in the training and test sets, enabling generalization beyond the training target support, and can be applied to any other material and molecular tasks. |
| title | Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules |
| topic | Machine Learning Materials Science Computational Engineering, Finance, and Science Chemical Physics |
| url | https://arxiv.org/abs/2502.05970 |