A local equivariant GNN with virtual-node graph slicing predicts DFT Hamiltonians of 1,000-3,000 atom amorphous materials, with a 0.53% norm-relative eigenvalue spectrum error and 2.17-2.58 meV element-wise error on held-out structures.
I., Zaanen, J., and Andersen, O
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning the Electronic Hamiltonian of Large Atomic Structures
A local equivariant GNN with virtual-node graph slicing predicts DFT Hamiltonians of 1,000-3,000 atom amorphous materials, with a 0.53% norm-relative eigenvalue spectrum error and 2.17-2.58 meV element-wise error on held-out structures.