MD17

The MD17 dataset is a benchmark that contains molecular dynamics data used to evaluate the performance of machine learning interatomic potentials in accurately modeling atomic environments.

Papers using MD17 (10)

Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs2022 · 65 citesEfficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian2023 · 3 citesEnsemble Learning of Machine Learning Force Fields2024SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning2024A Clifford Algebraic Approach to E(n)-Equivariant High-order Graph Neural Networks2024Learning Equivariant Non-Local Electron Density Functionals2024Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?20243D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding2025Layer-to-Layer Knowledge Mixing in Graph Neural Network for Chemical Property Prediction2025Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials2026