HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Formation Energy On Qm9

المقاييس

MAE

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

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