Article ; Online: Pretraining Strategies for Structure Agnostic Material Property Prediction.
Journal of chemical information and modeling
2024 Volume 64, Issue 3, Page(s) 627–637
Abstract: In recent years, machine learning (ML), especially graph neural network (GNN) models, has been successfully used for fast and accurate prediction of material properties. However, most ML models rely on relaxed crystal structures to develop descriptors ... ...
| Abstract | In recent years, machine learning (ML), especially graph neural network (GNN) models, has been successfully used for fast and accurate prediction of material properties. However, most ML models rely on relaxed crystal structures to develop descriptors for accurate predictions. Generating these relaxed crystal structures can be expensive and time-consuming, thus requiring an additional processing step for models that rely on them. To address this challenge, structure-agnostic methods have been developed, which use fixed-length descriptors engineered based on human knowledge about the material. However, the fixed-length descriptors are often hand-engineered and require extensive domain knowledge and generally are not used in the context of learnable models which are known to have a superior performance. Recent advancements have proposed learnable frameworks that can construct representations based on stoichiometry alone, allowing the flexibility of using deep learning frameworks as well as leveraging structure-agnostic learning. In this work, we propose three different pretraining strategies that can be used to pretrain these structure-agnostic, learnable frameworks to further improve the downstream material property prediction performance. We incorporate strategies such as self-supervised learning (SSL), fingerprint learning (FL), and multimodal learning (ML) and demonstrate their efficacy on downstream tasks for the Roost architecture, a popular structure-agnostic framework. Our results show significant improvement in small data sets and data efficiency in the larger data sets, underscoring the potential of our pretrain strategies that effectively leverage unlabeled data for accurate material property prediction. |
|---|---|
| MeSH term(s) | Humans ; Machine Learning ; Neural Networks, Computer |
| Language | English |
| Publishing date | 2024-02-01 |
| Publishing country | United States |
| Document type | Journal Article |
| ZDB-ID | 190019-5 |
| ISSN | 1549-960X ; 0095-2338 |
| ISSN (online) | 1549-960X |
| ISSN | 0095-2338 |
| DOI | 10.1021/acs.jcim.3c00919 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
More links
Kategorien
In stock of ZB MED Cologne/Königswinter
| Zs.A 1230: Show issues | Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (1.OG) ab Jg. 2022: Lesesaal (EG) |
Order via subito
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.