mlsanityData to 7 Oct 2026

Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments

arXiv 2109.09569 ↗First posted 20 Sep 2021physics.comp-ph stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

Artificial neural networks (NNs) are one of the most frequently used machine learning approaches to construct interatomic potentials and enable efficient large-scale atomistic simulations with almost ab initio accuracy. However, the simultaneous training of NNs on energies and forces, which are a prerequisite for, e.g., molecular dynamics simulations, can be demanding. In this work, we present an improved NN architecture based on the previous GM-NN model [V. Zaverkin and J. K"astner, J. Chem. Theory Comput. 16, 5410-5421 (2020)], which shows an improved prediction accuracy and considerably reduced training times. Moreover, we extend the applicability of Gaussian moment-based interatomic potentials to periodic systems and demonstrate the overall excellent transferability and robustness of the respective models. The fast training by the improved methodology is a pre-requisite for training-heavy workflows such as active learning or learning-on-the-fly.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 19 of its 77 references that are in the map. First posted on arXiv 20 Sep 2021.

Builds on

19 of 77 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  6. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  7. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  8. 2018On Lazy Training in Differentiable Programmingcited by 671
  9. 2017Self-Normalizing Neural Networkscited by 591
  10. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  11. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  12. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
7 more
  1. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
  2. 2018Less is more: sampling chemical space with active learningcited by 80
  3. 2017Hierarchical modeling of molecular energies using a deep neural networkcited by 37
  4. 2018Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulationcited by 37
  5. 2017Machine Learning Molecular Dynamics for the Simulation of Infrared Spectracited by 30
  6. 2021Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentialscited by 15
  7. 2020Which Minimizer Does My Neural Network Converge To?cited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 2.

9 papers.

  1. 2023Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Sciencecited by 25
  2. 2023Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentialscited by 16
  3. 2024Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passingcited by 13
  4. 2022Transfer learning for chemically accurate interatomic neural network potentialscited by 11
  5. 2024Physics-Informed Weakly Supervised Learning for Interatomic Potentialscited by 1
  6. 2025Breaking scaling relations with inverse catalysts: a machine learning exploration of trends in CO2 hydrogenation energy barrierscited by 1
  7. 2023Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Watercited by 0
  8. 2023Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Momentscited by 0
  9. 2025Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulationscited by 0