SPHNet uses learned sparse gates to prune atom pairs and tensor-product combinations, cutting training cost up to 7.1x while matching or improving Hamiltonian prediction accuracy on QH9, PubChemQH, and MD17.
ViSNet: an equivariant geometry-enhanced graph neural network with vector-scalar interactive message passing for molecules
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Geometric deep learning has been revolutionizing the molecular modeling field. Despite the state-of-the-art neural network models are approaching ab initio accuracy for molecular property prediction, their applications, such as drug discovery and molecular dynamics (MD) simulation, have been hindered by insufficient utilization of geometric information and high computational costs. Here we propose an equivariant geometry-enhanced graph neural network called ViSNet, which elegantly extracts geometric features and efficiently models molecular structures with low computational costs. Our proposed ViSNet outperforms state-of-the-art approaches on multiple MD benchmarks, including MD17, revised MD17 and MD22, and achieves excellent chemical property prediction on QM9 and Molecule3D datasets. Additionally, ViSNet achieved the top winners of PCQM4Mv2 track in the OGB-LCS@NeurIPS2022 competition. Furthermore, through a series of simulations and case studies, ViSNet can efficiently explore the conformational space and provide reasonable interpretability to map geometric representations to molecular structures.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity
SPHNet uses learned sparse gates to prune atom pairs and tensor-product combinations, cutting training cost up to 7.1x while matching or improving Hamiltonian prediction accuracy on QH9, PubChemQH, and MD17.