mlsanityData to 14 Oct 2026

Latent Ewald summation for machine learning of long-range interactions

arXiv 2408.15165 ↗First posted 27 Aug 2024cs.LG cond-mat.mtrl-sci physics.chem-phcited by 26

Not on the map. Why?

Abstract (arXiv)

Machine learning interatomic potentials (MLIPs) often neglect long-range interactions, such as electrostatic and dispersion forces. In this work, we introduce a straightforward and efficient method to account for long-range interactions by learning a latent variable from local atomic descriptors and applying an Ewald summation to this variable. We demonstrate that in systems including charged and polar molecular dimers, bulk water, and water-vapor interface, standard short-ranged MLIPs can lead to unphysical predictions even when employing message passing. The long-range models effectively eliminate these artifacts, with only about twice the computational cost of short-range MLIPs.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 9 of its 40 references that are in the map. First posted on arXiv 27 Aug 2024.

Builds on

9 of 40 references.

References · 9

  1. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  2. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  3. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  4. 2020Machine Learning Force Fieldscited by 207
  5. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 104
  6. 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
  7. 2024Cartesian atomic cluster expansion for machine learning interatomic potentialscited by 31
  8. 2023Physics-inspired Equivariant Descriptors of Non-bonded Interactionscited by 14
  9. 2022Capturing long-range interaction with reciprocal space neural networkcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 9.

26 papers.

Sort:

  1. 2024Euclidean Fast Attention -- Machine Learning Global Atomic Representations at Linear Costcited by 12
  2. 2025A universal augmentation framework for long-range electrostatics in machine learning interatomic potentialscited by 9
  3. 2026MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistrycited by 9
  4. 2026A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attentioncited by 8
  5. 2024Learning charges and long-range interactions from energies and forcescited by 7
  6. 2025Learning from the electronic structure of molecules across the periodic tablecited by 7
  7. 2025chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulationscited by 6
  8. 2025Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Spacecited by 6
  9. 2025DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentialscited by 5
  10. 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passingcited by 5
  11. 2025Equivariant Machine Learning Interatomic Potentials with Global Charge Redistributioncited by 4
  12. 2025Machine-Learning Interatomic Potentials for Long-Range Systemscited by 2
14 more
  1. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2
  2. 2026An SO(3)-equivariant reciprocal-space neural potential for long-range interactionscited by 2
  3. 2026Polarizable atomic multipoles for learning long-range electrostaticscited by 2
  4. 2026Equivariant learning of a transferable three-dimensional classical density functionalcited by 2
  5. 2025Reciprocal Space Attention for Learning Long-Range Interactionscited by 1
  6. 2026AceFF: A State-of-the-Art Machine Learning Potential for Small Moleculescited by 1
  7. 2026Machine Learning Multiscale Interactionscited by 1
  8. 2025SSLFusion: Scale & Space Aligned Latent Fusion Model for Multimodal 3D Object Detectioncited by 0
  9. 2025Electrostatics from Laplacian Eigenbasis for Neural Network Interatomic Potentialscited by 0
  10. 2025Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulationscited by 0
  11. 2025MCGM: Multi-stage Clustered Global Modeling for Long-range Interactions in Moleculescited by 0
  12. 2025Long-range electrostatics for machine learning interatomic potentials is easier than we thoughtcited by 0
  13. 2026Distilling latent electrostatics from foundation machine learning interatomic potentialscited by 0
  14. 2026Latent unified smooth Hamiltonians for excited state chemistrycited by 0