Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames

2025-06-11

AI Summary

To address the challenge of modeling SO(3) symmetry in Hamiltonian matrix prediction for electronic structure calculations, this paper proposes QHNetV2, an efficient SO(2)-equivariant graph neural network. Methodologically, it parameterizes off-diagonal Hamiltonian blocks within atom-centered local SO(2) coordinate frames—bypassing costly SO(3) tensor products and Clebsch–Gordan decompositions—and introduces SO(2)-equivariant message passing alongside continuous SO(2) tensor products for rotation-equivariant feature fusion. Its core innovation lies in the first unified framework reconciling local SO(2) modeling with global SO(3) equivariance, thereby enforcing strict physical symmetry constraints while substantially reducing computational complexity. On the QH9 and MD17 benchmarks, QHNetV2 achieves superior accuracy and generalization compared to state-of-the-art SO(3)-equivariant methods. The implementation is open-sourced and integrated into the AIRS library.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Computational social science

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.

Problem

• Predict Hamiltonian matrices efficiently for electronic structure calculations
• Achieve global SO(3) equivariance without costly SO(3) tensor products
• Develop scalable symmetry-aware learning for diverse molecular structures

Innovation

• Uses SO(2) local frames for efficient computation
• Introduces SO(2)-equivariant operations for feature updates
• Performs continuous SO(2) tensor product for fusion