מדידת רמות חופשיות נלמדות ברשתות נוירונים גרפיות לחומרים: הדמיה רנדומל-תת-ממדית של נפח רצוי

תקציר מקורי באנגליתarXiv:2609.36084v1 Announce Type: cross Abstract: Final predictive accuracy is the standard basis for comparing graph neural networks (GNNs) in materials-property prediction, but it does not show how strongly performance depends on access to trainable parameter-space directions. Here, we introduce trainable-degree dependence as a complementary characterization of materials GNN learning. Using random-subspace intrinsic-dimension analysis, we train CGCNN, ALIGNN, and DimeNet++ in randomly oriented parameter subspaces across six prediction tasks and measure how performance recovers as independent trainable degrees of freedom are restored. The resulting recovery curves separate endpoint accuracy from the trainable-dimensional demand required to recover it. They reveal distinctions that final e