Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Harmonization of SO(3)-Equivariance and Expressiveness: a Hybrid Deep Learning Framework for Electronic-Structure Hamiltonian Prediction (2401.00744v11)

Published 1 Jan 2024 in physics.comp-ph, cond-mat.mtrl-sci, and cs.LG

Abstract: Deep learning for predicting the electronic-structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks remains unsolved. To navigate the harmonization between equivariance and expressiveness, we propose a deep learning method synergizing two distinct categories of neural mechanisms as a two-stage encoding and regression framework. The first stage corresponds to group theory-based neural mechanisms with inherent SO(3)-equivariant properties prior to the parameter learning process, while the second stage is characterized by a non-linear 3D graph Transformer network we propose, featuring high capability on non-linear expressiveness. The novel combination lies in the point that, the first stage predicts baseline Hamiltonians with abundant SO(3)-equivariant features extracted, assisting the second stage in empirical learning of equivariance; and in turn, the second stage refines the first stage's output as a fine-grained prediction of Hamiltonians using powerful non-linear neural mappings, compensating for the intrinsic weakness on non-linear expressiveness capability of mechanisms in the first stage. Our method enables precise, generalizable predictions while capturing SO(3)-equivariance under rotational transformations, and achieves state-of-the-art performance in Hamiltonian prediction on six benchmark databases.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications, 13(1):2453, 2022.
  2. Unconventional superconductivity in magic-angle graphene superlattices. Nature, 556(7699):43–50, 2018.
  3. Steerable cnns. In ICLR, 2017.
  4. Exploiting cyclic symmetry in convolutional neural networks. In ICML Workshop, volume 48, pp.  1889–1898, 2016.
  5. Ferreira, F. Multiscale modelling of twisted bilayers of 2d materials. Nature Reviews Physics, 4(10):632–632, 2022.
  6. Se(3)-transformers: 3d roto-translation equivariant attention networks. In NeurIPS, 2020.
  7. e3nn: Euclidean neural networks. CoRR, abs/2207.09453, 2022.
  8. General framework for e (3)-equivariant neural network representation of density functional theory hamiltonian. Nature Communications, 14(1):2848, 2023.
  9. Neural network representation of electronic structure from ab initio molecular dynamics. Science Bulletin, 67(1):29–37, 2022.
  10. Inhomogeneous electron gas. Physical Review, 136(3B):B864, 1964.
  11. Spatial transformer networks. In NeurIPS, pp.  2017–2025, 2015.
  12. Self-consistent equations including exchange and correlation effects. Physical Review, 140(4A):A1133, 1965.
  13. Covariant compositional networks for learning graphs. In ICLR Workshop, 2018.
  14. Deep-learning density functional theory hamiltonian for efficient ab initio electronic-structure calculation. Nature Computational Science, 2(6):367–377, 2022.
  15. Learning local equivariant representations for large-scale atomistic dynamics. Nature Communications, 14(1), 2023.
  16. Tunable strongly coupled superconductivity in magic-angle twisted trilayer graphene. Nature, 590(7845):249–255, 2021.
  17. Reducing SO(3) convolutions to SO(2) for efficient equivariant gnns. In ICML, pp.  27420–27438, 2023.
  18. Equivariance through parameter-sharing. In ICML, pp.  2892–2901, 2017.
  19. E(n) equivariant graph neural networks. In ICML, volume 139, pp.  9323–9332, 2021.
  20. Schrödinger, E. Quantisierung als eigenwertproblem. Annalen der Physik, 384(4):361–376, 1926.
  21. Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions. Nature Communications, 10(1):5024, 2019.
  22. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  23. Se (3)-equivariant prediction of molecular wavefunctions and electronic densities. volume 34, pp.  14434–14447, 2021.
  24. Attention is all you need. In NeurIPS, pp.  5998–6008, 2017.
  25. Deepmd-kit: A deep learning package for many-body potential energy representation and molecular dynamics. Computer Physics Communications, 228:178–184, 2018.
  26. Universal machine learning for the response of atomistic systems to external fields. Nature Communications, 14, 2023.
  27. Embedded atom neural network potentials: Efficient and accurate machine learning with a physically inspired representation. The journal of physical chemistry letters, 10(17):4962–4967, 2019.
  28. Spherical channels for modeling atomic interactions. In NeurIPS, 2022.
Citations (1)

Summary

We haven't generated a summary for this paper yet.