mlsanityData to 14 Oct 2026

Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction

arXiv 2411.04219 ↗First posted 6 Nov 2024cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent advancements in equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. Using spherical harmonics (SH) and tensor products (TP), these equivariant networks gain enhanced physical understanding, like symmetries and many-body interactions. Beyond encoding physical insights, SH and TP are also crucial to represent equivariant polynomial functions. In this work, we analyze the equivariant polynomial functions for the equivariant architecture, and introduce a novel equivariant network, named PACE. The proposed PACE utilizes edge booster and the Atomic Cluster Expansion (ACE) technique to approximate a greater number of SE(3) × Sn equivariant polynomial functions with enhanced degrees. As experimented in commonly used benchmarks, PACE demonstrates state-of-the-art performance in predicting atomic energy and force fields, with robust generalization capability across various geometric distributions under molecular dynamics (MD) across different temperature conditions. Our code is publicly available as part of the AIRS library https://github.com/divelab/AIRS/.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 43 of its 64 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

43 of 64 references.

References · 43

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  6. 2017Deep Setscited by 1,421
  7. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  8. 2021E(n) Equivariant Graph Neural Networkscited by 965
  9. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  10. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  11. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  12. 2020Directional Message Passing for Molecular Graphscited by 561
31 more
  1. 2019Graph U-Netscited by 492
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  4. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  5. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  6. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  7. 2020Towards Deeper Graph Neural Networkscited by 296
  8. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  9. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  10. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 256
  11. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  12. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 214
  13. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 183
  14. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 182
  15. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  16. 2019On the Universality of Invariant Networkscited by 152
  17. 2023Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systemscited by 121
  18. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 104
  19. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 101
  20. 2020Line Graph Neural Networks for Link Predictioncited by 89
  21. 2020On the Universality of Rotation Equivariant Point Cloud Networkscited by 80
  22. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  23. 2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 76
  24. 2021SE(3)-equivariant prediction of molecular wavefunctions and electronic densitiescited by 67
  25. 2023A new perspective on building efficient and expressive 3D equivariant graph neural networkscited by 47
  26. 2019On Universal Equivariant Set Networkscited by 45
  27. 2023Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltoniancited by 39
  28. 2023HYTREL: Hypergraph-enhanced Tabular Data Representation Learningcited by 36
  29. 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Productscited by 36
  30. 2023QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Moleculescited by 26
  31. 2022Tensor-reduced atomic density representationscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Framescited by 6
  2. 2025A Materials Foundation Model via Hybrid Invariant-Equivariant Architecturescited by 4
  3. 2025Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentialscited by 1
  4. 2025Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computationscited by 1
  5. 2026Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruningcited by 0
  6. 2026Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuningcited by 0