Improved Uncertainty Estimation of Graph Neural Network Potentials Using Engineered Latent Space Distances

Documenti analoghi

• Accessing Numerical Energy Hessians with Graph Neural Network Potentials and Their Application in Heterogeneous Catalysis
  di: Wander, Brook, et al.
  Pubblicazione: (2024)
• Reduced Order Modeling of Energetic Materials Using Physics-Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)
  di: Gray, Zoë J., et al.
  Pubblicazione: (2025)
• Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles
  di: Vinchurkar, Tirtha, et al.
  Pubblicazione: (2025)
• ADA-GNN: Atom-Distance-Angle Graph Neural Network for Crystal Material Property Prediction
  di: Huang, Jiao, et al.
  Pubblicazione: (2024)
• Stable Long-Horizon Spatiotemporal Prediction on Meshes Using Latent Multiscale Recurrent Graph Neural Networks
  di: Salesses, Lionel, et al.
  Pubblicazione: (2026)