Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911761414750208 |
|---|---|
| author | Falk, John Bonati, Luigi Novelli, Pietro Parrinello, Michele Pontil, Massimiliano |
| author_facet | Falk, John Bonati, Luigi Novelli, Pietro Parrinello, Michele Pontil, Massimiliano |
| contents | Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, while generating reference calculations is computationally demanding. To bypass this difficulty, we propose a transfer learning algorithm that leverages the ability of graph neural networks (GNNs) to represent chemical environments together with kernel mean embeddings. We extract a feature map from GNNs pre-trained on the OC20 dataset and use it to learn the potential energy surface from system-specific datasets of catalytic processes. Our method is further enhanced by incorporating into the kernel the chemical species information, resulting in improved performance and interpretability. We test our approach on a series of realistic datasets of increasing complexity, showing excellent generalization and transferability performance, and improving on methods that rely on GNNs or ridge regression alone, as well as similar fine-tuning approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_01589 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Transfer learning for atomistic simulations using GNNs and kernel mean embeddings Falk, John Bonati, Luigi Novelli, Pietro Parrinello, Michele Pontil, Massimiliano Machine Learning Chemical Physics Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, while generating reference calculations is computationally demanding. To bypass this difficulty, we propose a transfer learning algorithm that leverages the ability of graph neural networks (GNNs) to represent chemical environments together with kernel mean embeddings. We extract a feature map from GNNs pre-trained on the OC20 dataset and use it to learn the potential energy surface from system-specific datasets of catalytic processes. Our method is further enhanced by incorporating into the kernel the chemical species information, resulting in improved performance and interpretability. We test our approach on a series of realistic datasets of increasing complexity, showing excellent generalization and transferability performance, and improving on methods that rely on GNNs or ridge regression alone, as well as similar fine-tuning approaches. |
| title | Transfer learning for atomistic simulations using GNNs and kernel mean embeddings |
| topic | Machine Learning Chemical Physics |
| url | https://arxiv.org/abs/2306.01589 |