QM9

Overview edit

Variants: QM9

Associated Benchmarks

This dataset is used in 8 benchmarks:

• Drug Discovery - Metrics: Error ratio
• Graph Regression - Metrics: Inference Time (ms)
• Molecular Property Prediction - Metrics: MAE
• Multi-Task Learning - Metrics: ∆m%
• Formation Energy - Metrics: MAE
• Graph Property Prediction - Metrics: Standardized MAE, logMAE, alpha (ma), gap (meV)
• Prediction - Metrics: Edit Distance
• Unconditional Molecule Generation - Metrics: Validity, PoseBusters Internal Energy

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• All-atom Diffusion Transformers: Unified generative modelling of molecules and materials (2025) -
• FIT-GNN: Faster Inference Time for GNNs Using Coarsening (2024) -
• Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss (2024) -
• Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning (2024) -
• Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation (2023) -
• A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems (2023) -
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations (2023) -
• TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials (2023) -
• Geometric Latent Diffusion Models for 3D Molecule Generation (2023) -
• Wigner kernels: body-ordered equivariant machine learning without a basis (2023) -
• Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability (2023) -
• Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs (2022) -
• ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs (2022) -
• Equivariant Diffusion for Molecule Generation in 3D (2022) -
• TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials (2022) -
• Multi-Task Learning as a Bargaining Game (2022) -
• Geometric and Physical Quantities Improve E(3) Equivariant Message Passing (2021) -
• ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction (2021) -
• E(n) Equivariant Graph Neural Networks (2021) -
• Spherical Message Passing for 3D Graph Networks (2021) -