mlsanityData to 14 Oct 2026

FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields

arXiv 2407.02263 ↗First posted 2 Jul 2024cs.LG physics.chem-ph q-bio.BMcited by 1

Not on the map. Why?

Abstract (arXiv)

Machine Learning Force Fields (MLFFs) are of great importance for chemistry, physics, materials science, and many other related fields. The Clebsch-Gordan Transform (CG transform) effectively encodes many-body interactions and is thus an important building block for many models of MLFFs. However, the permutation-equivariance requirement of MLFFs limits the design space of CG transform, that is, intensive CG transform has to be conducted for each neighboring edge and the operations should be performed in the same manner for all edges. This constraint results in reduced expressiveness of the model while simultaneously increasing computational demands. To overcome this challenge, we first implement the CG transform layer on the permutation-invariant abstract edges generated from real edge information. We show that this approach allows complete freedom in the design of the layer without compromising the crucial symmetry. Developing on this free design space, we further propose group CG transform with sparse path, abstract edges shuffling, and attention enhancer to form a powerful and efficient CG transform layer. Our method, known as FreeCG, achieves state-of-the-art (SOTA) results in force prediction for MD17, rMD17, MD22, and is well extended to property prediction in QM9 datasets with several improvements greater than 15% and the maximum beyond 20%. The extensive real-world applications showcase high practicality. FreeCG introduces a novel paradigm for carrying out efficient and expressive CG transform in future geometric neural network designs. To demonstrate this, the recent SOTA, QuinNet, is also enhanced under our paradigm. Code will be publicly available.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 60 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

24 of 60 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  3. 2021E(n) Equivariant Graph Neural Networkscited by 965
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  5. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  6. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  7. 2020Directional Message Passing for Molecular Graphscited by 561
  8. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  9. 2018Spherical CNNscited by 456
  10. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  11. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  12. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
12 more
  1. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 256
  2. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
  3. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 182
  4. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 104
  5. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 101
  6. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 95
  7. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  8. 2021ForceNet: A Graph Neural Network for Large-Scale Quantum Calculationscited by 58
  9. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 54
  10. 2022So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systemscited by 39
  11. 2021Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistrycited by 30
  12. 2022Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interatomic Potentialscited by 7