mlsanityData to 14 Oct 2026

Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science

arXiv 2305.14247 ↗First posted 23 May 2023physics.chem-ph stat.MLcited by 25

Not on the map. Why?

Abstract (arXiv)

The MACE architecture represents the state of the art in the field of machine learning force fields for a variety of in-domain, extrapolation and low-data regime tasks. In this paper, we further evaluate MACE by fitting models for published benchmark datasets. We show that MACE generally outperforms alternatives for a wide range of systems from amorphous carbon, universal materials modelling, and general small molecule organic chemistry to large molecules and liquid water. We demonstrate the capabilities of the model on tasks ranging from constrained geometry optimisation to molecular dynamics simulations and find excellent performance across all tested domains. We show that MACE is very data efficient, and can reproduce experimental molecular vibrational spectra when trained on as few as 50 randomly selected reference configurations. We further demonstrate that the strictly local atom-centered model is sufficient for such tasks even in the case of large molecules and weakly interacting molecular assemblies.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 34 of its 93 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

34 of 93 references.

References · 34

  1. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  2. 2021E(n) Equivariant Graph Neural Networkscited by 965
  3. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  4. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  5. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  6. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  7. 2019Fantastic Generalization Measures and Where to Find Themcited by 513
  8. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  9. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  10. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  11. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  12. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 256
22 more
  1. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
  2. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  3. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  4. 2016Tensor Decomposition for Signal Processing and Machine Learningcited by 224
  5. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 182
  6. 2022e3nn: Euclidean Neural Networkscited by 174
  7. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  8. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  9. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 101
  10. 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 95
  11. 2019Scaling description of generalization with number of parameters in deep learningcited by 83
  12. 2018Less is more: sampling chemical space with active learningcited by 82
  13. 2019Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspectivecited by 73
  14. 2021Simple GNN Regularisation for 3D Molecular Property Prediction & Beyondcited by 44
  15. 2023Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic sizecited by 33
  16. 2022Equivariant Graph Attention Networks for Molecular Property Predictioncited by 20
  17. 2019TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxationscited by 16
  18. 2022Unified theory of atom-centered representations and message-passing machine-learning schemescited by 13
  19. 2022Transfer learning for chemically accurate interatomic neural network potentialscited by 11
  20. 2022Tensor-reduced atomic density representationscited by 10
  21. 2021Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Momentscited by 9
  22. 2023Wigner kernels: body-ordered equivariant machine learning without a basiscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 10; 2026: 4.

25 papers.

Sort:

  1. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 54
  2. 2024The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domainscited by 40
  3. 2023From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Predictioncited by 39
  4. 2024Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Productscited by 36
  5. 2024Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applicationscited by 24
  6. 2025Force-Free Molecular Dynamics Through Autoregressive Equivariant Networkscited by 15
  7. 2025Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systemscited by 14
  8. 2024Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passingcited by 13
  9. 2024On the Completeness of Invariant Geometric Deep Learning Modelscited by 11
  10. 2026MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistrycited by 9
  11. 2025Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Spacecited by 6
  12. 2024On the design space between molecular mechanics and machine learning force fieldscited by 4
13 more
  1. 2023Equivariant Matrix Function Neural Networkscited by 3
  2. 2024Accurate Crystal Structure Prediction of New 2D Hybrid Organic Inorganic Perovskitescited by 3
  3. 2025BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Modelscited by 3
  4. 2025A Cartesian-3j Framework for Machine Learning Interatomic Potentialscited by 3
  5. 2025Efficient and Accurate Spatial Mixing of Machine Learned Interatomic Potentials for Materials Sciencecited by 2
  6. 2025Optimal Invariant Bases for Atomistic Machine Learningcited by 1
  7. 2025Optimizing Data Distribution and Kernel Performance for Efficient Training of Chemistry Foundation Models: A Case Study with MACEcited by 1
  8. 2023Machine-Learned Atomic Cluster Expansion Potentials for Fast and Quantum-Accurate Thermal Simulations of Wurtzite AlNcited by 0
  9. 2025Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearitycited by 0
  10. 2025On-the-Fly Fine-Tuning of Foundational Neural Network Potentials: A Bayesian Neural Network Approachcited by 0
  11. 2026Neutron and X-ray Diffraction Reveal the Limits of Long-Range Machine Learning Potentials for Medium-Range Order in Silica Glasscited by 0
  12. 2026Triply-Scalable Equivariant Gaussian Process Modelingcited by 0
  13. 2026SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentialscited by 0