English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph neural networks trained on large crystal structure databases areextremely effective in replacing ab initio calculations in the discovery andcharacterization of materials. However, crystal structure datasets comprisingmillions of materials exist only for the Perdew-Burke-Ernzerhof (PBE)functional. In this work, we investigate the effectiveness of transfer learningto extend these models to other density functionals. We show that pre-trainingsignificantly reduces the size of the dataset required to achieve chemicalaccuracy and beyond. We also analyze in detail the relationship between thetransfer-learning performance and the size of the datasets used for the initialtraining of the model and transfer learning. We confirm a linear dependence ofthe error on the size of the datasets on a log-log scale, with a similar slopefor both training and the pre-training datasets. This shows that furtherincreasing the size of the pre-training dataset, i.e. performing additionalcalculations with a low-cost functional, is also effective, through transferlearning, in improving machine-learning predictions with the quality of a moreaccurate, and possibly computationally more involved functional. Lastly, wecompare the efficacy of interproperty and intraproperty transfer learning.

Transfer learning on large datasets for the accurate prediction of material properties