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

Crystal property prediction is a crucial aspect of developing novelmaterials. However, there are two technical challenges to be addressed forspeeding up the investigation of crystals. First, labeling crystal propertiesis intrinsically difficult due to the high cost and time involved in physicalsimulations or lab experiments. Second, crystals adhere to a specific quantumchemical principle known as periodic invariance, which is often not captured byexisting machine learning methods. To overcome these challenges, we propose thecrystal-specific pre-training framework for learning crystal representationswith self-supervision. The framework designs a mutex mask strategy forenhancing representation learning so as to alleviate the limited labelsavailable for crystal property prediction. Moreover, we take into account thespecific periodic invariance in crystal structures by developing a periodicinvariance multi-graph module and periodic attribute learning within ourframework. This framework has been tested on eight different tasks. Theexperimental results on these tasks show that the framework achieves promisingprediction performance and is able to outperform recent strong baselines.

A Crystal-Specific Pre-Training Framework for Crystal Material Property Prediction