mlsanityData to 14 Oct 2026

Role of Structural and Conformational Diversity for Machine Learning Potentials

arXiv 2311.00862 ↗First posted 30 Oct 2023physics.chem-ph cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In the field of Machine Learning Interatomic Potentials (MLIPs), understanding the intricate relationship between data biases, specifically conformational and structural diversity, and model generalization is critical in improving the quality of Quantum Mechanics (QM) data generation efforts. We investigate these dynamics through two distinct experiments: a fixed budget one, where the dataset size remains constant, and a fixed molecular set one, which focuses on fixed structural diversity while varying conformational diversity. Our results reveal nuanced patterns in generalization metrics. Notably, for optimal structural and conformational generalization, a careful balance between structural and conformational diversity is required, but existing QM datasets do not meet that trade-off. Additionally, our results highlight the limitation of the MLIP models at generalizing beyond their training distribution, emphasizing the importance of defining applicability domain during model deployment. These findings provide valuable insights and guidelines for QM data generation efforts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 43 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

15 of 43 references.

References · 15

  1. 2021E(n) Equivariant Graph Neural Networkscited by 965
  2. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  3. 2020Directional Message Passing for Molecular Graphscited by 561
  4. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  5. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  6. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  7. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  8. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 256
  9. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  10. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 182
  11. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  12. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 101
3 more
  1. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 82
  2. 2021Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphscited by 31
  3. 2023PubChemQC B3LYP/6-31G*//PM6 dataset: the Electronic Structures of 86 Million Molecules using B3LYP/6-31G* calculationscited by 12

Built on by

Not cited yet.