Skip to main content
Search

# Matminer

1 related articles

Subscribe to updates
  1. arXiv

    Materials representations rank their own training data: without target labels, a crystal-graph encoder picks the compounds that best supervise a new element

    When target compounds contain elements absent from training, it has been unclear which compounds of other elements supply transferable supervision. A pretrained crystal-graph encoder's representation ranks elements by the supervision their compounds provide without using target-property labels; at fixed training-set size, excluding the compounds of its six top-ranked elements raises formation-energy and bandgap errors by 100–110 meV atom-1 and 42–85 meV, while excluding six lower-ranked elements changes little. The rankings hold across properties, regressors and datasets, indicating that the representation itself organizes supervision and that the ranking can be identified before model training.

You’re all caught up