mlsanityData to 14 Oct 2026

Hierarchical geometric deep learning enables scalable analysis of molecular dynamics

arXiv 2512.06520 ↗First posted 6 Dec 2025cs.LG cond-mat.stat-mech physics.comp-phcited by 1

Not on the map. Why?

Abstract (arXiv)

Molecular dynamics simulations can generate atomically detailed trajectories of complex systems, but analyzing these dynamics can be challenging when systems lack well-established quantitative descriptors (features). Graph neural networks (GNNs) in which messages are passed between nodes that represent atoms that are spatial neighbors promise to obviate manual feature engineering, but the use of GNNs with biomolecular systems of more than a few hundred residues has been limited in the context of analyzing dynamics by both difficulties in capturing the details of long-range interactions with message passing and the memory and runtime requirements associated with large graphs. Here, we show how local information can be aggregated to reduce memory and runtime requirements without sacrificing atomic detail. We demonstrate that this approach opens the door to analyzing simulations of protein-nucleic acid complexes with thousands of residues on single GPUs within minutes. For systems with hundreds of residues, for which there are sufficient data to make quantitative comparisons, we show that the approach improves performance and interpretability.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 78 references that are in the map. First posted on arXiv 6 Dec 2025.

Builds on

31 of 78 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  7. 2022Token Merging: Your ViT But Fastercited by 1,021
  8. 2017Residual Gated Graph ConvNetscited by 346
  9. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  10. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  11. 2017VAE with a VampPriorcited by 248
  12. 2017VAMPnets: Deep learning of molecular kineticscited by 136
19 more
  1. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  2. 2017Topology Adaptive Graph Convolutional Networkscited by 113
  3. 2024Scaling Exponents Across Parameterizations and Optimizerscited by 76
  4. 2022Benchmarking Graphormer on Large-Scale Molecular Modeling Datasetscited by 64
  5. 2020Hierarchical Inter-Message Passing for Learning on Molecular Graphscited by 59
  6. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 54
  7. 2017Variational approach for learning Markov processes from time series datacited by 52
  8. 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
  9. 2024Evaluating representation learning on the protein structure universecited by 16
  10. 2019Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnetscited by 14
  11. 2019Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materialscited by 13
  12. 2023Inexact iterative numerical linear algebra for neural network-based spectral estimation and rare-event predictioncited by 9
  13. 2024Neural P3M: A Long-Range Interaction Modeling Enhancer for Geometric GNNscited by 9
  14. 2022GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomoleculescited by 8
  15. 2023Beyond MD17: the reactive xxMD datasetcited by 6
  16. 2024Graph Neural Network-State Predictive Information Bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kineticscited by 5
  17. 2024Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamicscited by 5
  18. 2023Transformers are efficient hierarchical chemical graph learnerscited by 4
  19. 2024Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfercited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Machine learning kinetics from molecular dynamics datacited by 0