Formation Energy On Qm9

评估指标

MAE

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
HDAD+KRR0.58Machine learning prediction errors better than DFT accuracy-
MPNN0.49Neural Message Passing for Quantum Chemistry
SchNet0.314Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
ALIGNN0.30Atomistic Line Graph Neural Network for Improved Materials Property Predictions
MEGNet-simple0.28Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
HIP-NN0.256Hierarchical modeling of molecular energies using a deep neural network-
SchNet-edge-update0.242Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
MEGNet-Full0.21Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
PhysNet0.19PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
DimeNet0.185Directional Message Passing for Molecular Graphs
xGPR -- Gaussian process, graph convolution kernel0.167Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability
DeepMoleNet0.141Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning-
PhysNet-ens50.14PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
HMGNN0.138Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
MXMNet0.137Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
PAMNet0.136A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems-
Wigner Kernels0.100 ± 0.003Wigner kernels: body-ordered equivariant machine learning without a basis-
TensorNet0.09TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
0 of 18 row(s) selected.
Formation Energy On Qm9 | SOTA | HyperAI超神经