mlsanityData to 7 Oct 2026

TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials

arXiv 2202.02541 ↗First posted 5 Feb 2022cs.LG cs.AI physics.chem-phcited by 179

Not on the map. Why?

Abstract (arXiv)

The prediction of quantum mechanical properties is historically plagued by a trade-off between accuracy and speed. Machine learning potentials have previously shown great success in this domain, reaching increasingly better accuracy while maintaining computational efficiency comparable with classical force fields. In this work we propose TorchMD-NET, a novel equivariant transformer (ET) architecture, outperforming state-of-the-art on MD17, ANI-1, and many QM9 targets in both accuracy and computational efficiency. Through an extensive attention weight analysis, we gain valuable insights into the black box predictor and show differences in the learned representation of conformers versus conformations sampled from molecular dynamics or normal modes. Furthermore, we highlight the importance of datasets including off-equilibrium conformations for the evaluation of molecular potentials.

Key facts. Cited by 179 papers in the map (data through 7 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 5 Feb 2022.

Builds on

24 of 39 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Layer Normalizationcited by 5,579
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Rethinking Attention with Performerscited by 1,584
  7. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  8. 2021E(n) Equivariant Graph Neural Networkscited by 951
  9. 2020Quantifying Attention Flow in Transformerscited by 759
  10. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  11. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  12. 2020Directional Message Passing for Molecular Graphscited by 556
12 more
  1. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  2. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  3. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  4. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
  5. 2019Ab-Initio Solution of the Many-Electron Schr"odinger Equation with Deep Neural Networkscited by 195
  6. 2019Deep neural network solution of the electronic Schr"odinger equationcited by 124
  7. 2020LieTransformer: Equivariant self-attention for Lie Groupscited by 100
  8. 2019Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspectivecited by 73
  9. 2018Machine Learning of coarse-grained Molecular Dynamics Force Fieldscited by 68
  10. 2020OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Featurescited by 63
  11. 2020Coarse Graining Molecular Dynamics with Graph Neural Networkscited by 56
  12. 2020TorchMD: A deep learning framework for molecular simulationscited by 55

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 22; 2023: 47; 2024: 47; 2025: 39; 2026: 24.

179 papers.

Sort:

By area:

  1. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  2. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  3. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  4. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 201
  5. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  6. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  7. 2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
  8. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 100
  9. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 92
  10. 2023Attending to Graph Transformerscited by 81
  11. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  12. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
38 more
  1. 2023FAENet: Frame Averaging Equivariant GNN for Materials Modelingcited by 72
  2. 2023A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systemscited by 65
  3. 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 55
  4. 2023Clifford Group Equivariant Neural Networkscited by 54
  5. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 53
  6. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  7. 2023OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentialscited by 44
  8. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 41
  9. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Modelscited by 41
  10. 2024ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generationcited by 41
  11. 2024The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domainscited by 40
  12. 2022So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systemscited by 39
  13. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  14. 2023From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Predictioncited by 39
  15. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  16. 2022Machine Learning Coarse-Grained Potentials of Protein Thermodynamicscited by 37
  17. 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Productscited by 35
  18. 2023Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic sizecited by 33
  19. 2023Fractional Denoising for 3D Molecular Pre-trainingcited by 33
  20. 2024A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applicationscited by 28
  21. 2023QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Moleculescited by 26
  22. 2023Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Sciencecited by 25
  23. 2022Simulate Time-integrated Coarse-grained Molecular Dynamics with Multi-Scale Graph Networkscited by 23
  24. 2023Is Distance Matrix Enough for Geometric Deep Learning?cited by 22
  25. 2023Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+cited by 22
  26. 2023Navigating protein landscapes with a machine-learned transferable coarse-grained modelcited by 22
  27. 2024Clifford Group Equivariant Simplicial Message Passing Networkscited by 22
  28. 2022Graph Neural Networks for Moleculescited by 21
  29. 2023Scaling Spherical CNNscited by 21
  30. 2023Multimodal Molecular Pretraining via Modality Blendingcited by 21
  31. 2022Equivariant Graph Attention Networks for Molecular Property Predictioncited by 19
  32. 2023Generalist Equivariant Transformer Towards 3D Molecular Interaction Learningcited by 18
  33. 2023Sliced Denoising: A Physics-Informed Molecular Pre-Training Methodcited by 18
  34. 2024Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fieldscited by 18
  35. 2024UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learningcited by 18
  36. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  37. 2022Geometry-Complete Perceptron Networks for 3D Molecular Graphscited by 15
  38. 2023Dynamic Graph Representation Learning with Neural Networks: A Surveycited by 15

50 most cited of 179 All 179 (JSON)