Machine Learning Multiscale Interactions
Not on the map. Why?
Abstract (arXiv)
Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 66 references that are in the map. First posted on arXiv 25 May 2026.
Builds on
31 of 66 references.
References · 31
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
- 2020Point Transformercited by 1,462
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
- 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
- 2020Directional Message Passing for Molecular Graphscited by 556
- 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
19 more
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
- 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 342
- 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
- 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
- 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
- 2022Graph neural networks for materials science and chemistrycited by 181
- 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
- 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
- 2023Demystifying Oversmoothing in Attention-Based Graph Neural Networkscited by 47
- 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
- 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
- 2022So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systemscited by 39
- 2023Efficient Approximations of Complete Interatomic Potentials for Crystal Property Predictioncited by 37
- 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
- 2024Latent Ewald summation for machine learning of long-range interactionscited by 26
- 20202D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classificationcited by 9
- 2025A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimationcited by 4
- 2025PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property predictioncited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.