Equivariant MPNNs (MACE, PaiNN, SO3Net) outperform invariant ones (SchNet, FieldSchNet) in transferability and spectral accuracy for IR spectroscopy of organic molecules while maintaining high fidelity on training data.
Phys.14053020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.chem-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking machine-learned interatomic potentials for molecular infrared spectroscopy
Equivariant MPNNs (MACE, PaiNN, SO3Net) outperform invariant ones (SchNet, FieldSchNet) in transferability and spectral accuracy for IR spectroscopy of organic molecules while maintaining high fidelity on training data.