aiqbench analysis
QHNetV2 accelerates electronic structure calculations by achieving global SO(3) equivariance without the computational overhead of SO(3) Clebsch-Gordan tensor products. The model leverages efficient SO(2)-equivariant operations within local frames to demonstrate superior performance and generalization on large molecular datasets like QH9 and MD17. This approach offers a scalable pathway for symmetry-aware machine learning in physics and materials science, with code available via the AIRS library.
Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames
arXiv:2506.09398v4 Announce Type: replace Abstract: We consider the task of predicting Hamiltonian matrices to accelerate electronic structure calculations, which plays an important role in physics, chemistry, and materials science. Motivated by the inherent relationship between the off-diagonal blocks of the Hamiltonian matrix and the SO(2) local frame, we propose a novel and efficient network, called QHNetV2, that achieves global SO(3) equivariance without the costly SO(3) Clebsch-Gordan tensor products. This is achieved by introducing a set of new efficient and powerful SO(2)-equivariant operations and performing all off-diagonal feature updates and message passing within SO(2) local frames, thereby eliminating the need of SO(3) tensor products. Moreover, a continuous SO(2) tensor product is performed within the SO(2) local frame at each node to fuse node features, mimicking the symmetric contraction operation. Extensive experiments on the large QH9 and MD17 datasets demonstrate that our model achieves superior performance across a wide range of molecular structures and trajectories, highlighting its strong generalization capability. The proposed SO(2) operations on SO(2) local frames offer a promising direction for scalable and symmetry-aware learning of electronic structures. Our code will be released as part of the AIRS library https://github.com/divelab/AIRS.
Abstract:We consider the task of predicting Hamiltonian matrices to accelerate electronic structure calculations, which plays an important role in physics, chemistry, and materials science. Motivated by the inherent relationship between the off-diagonal blocks of the Hamiltonian matrix and the SO(2) local frame, we propose a novel and efficient network, called QHNetV2, that achieves global SO(3) equivariance without the costly SO(3) Clebsch-Gordan tensor products. This is achieved by introducing a set of new efficient and powerful SO(2)-equivariant operations and performing all off-diagonal feature updates and message passing within SO(2) local frames, thereby eliminating the need of SO(3) tensor products. Moreover, a continuous SO(2) tensor product is performed within the SO(2) local frame at each node to fuse node features, mimicking the symmetric contraction operation. Extensive experiments on the large QH9 and MD17 datasets demonstrate that our model achieves superior performance across a wide range of molecular structures and trajectories, highlighting its strong generalization capability. The proposed SO(2) operations on SO(2) local frames offer a promising direction for scalable and symmetry-aware learning of electronic structures. Our code will be released as part of the AIRS library this https URL.
Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
arXiv:2506.09398 [cs.LG]
(or arXiv:2506.09398v4 [cs.LG] for this version)
Full text under the publisher's open licence · 201 words
Related coverage
Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control
arXiv · Aug 4, 2026
Learning shadows to predict quantum ground state correlations
arXiv · Sep 4, 2026
Local Relaxation Hierarchies for Quantum Ground State Energies: Convergence Guarantees and Message Passing Algorithms
arXiv · Oct 1, 2026
GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry
arXiv · Sep 24, 2026