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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Artificial intelligence and machine learning have shown great promise intheir ability to accelerate novel materials discovery. As researchers anddomain scientists seek to unify and consolidate chemical knowledge, the casefor models with potential to generalize across different tasks within materialsscience - so-called "foundation models" - grows with ambitions. This manuscriptreviews our recent progress with development of Open MatSci ML Toolkit, anddetails experiments that lay the groundwork for foundation model research anddevelopment with our framework. First, we describe and characterize a newpretraining task that uses synthetic data generated from symmetry operations,and reveal complex training dynamics at large scales. Using the pretrainedmodel, we discuss a number of use cases relevant to foundation modeldevelopment: semantic architecture of datasets, and fine-tuning for propertyprediction and classification. Our key results show that for simpleapplications, pretraining appears to provide worse modeling performance thantraining models from random initialization. However, for more complexinstances, such as when a model is required to learn across multiple datasetsand types of targets simultaneously, the inductive bias from pretrainingprovides significantly better performance. This insight will hopefully informsubsequent efforts into creating foundation models for materials scienceapplications.

Towards Foundation Models for Materials Science: The Open MatSci ML Toolkit