Neural Message Passing on High Order Paths
Not on the map. Why?
Abstract (arXiv)
Graph neural network have achieved impressive results in predicting molecular properties, but they do not directly account for local and hidden structures in the graph such as functional groups and molecular geometry. At each propagation step, GNNs aggregate only over first order neighbours, ignoring important information contained in subsequent neighbours as well as the relationships between those higher order connections. In this work, we generalize graph neural nets to pass messages and aggregate across higher order paths. This allows for information to propagate over various levels and substructures of the graph. We demonstrate our model on a few tasks in molecular property prediction.
Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Feb 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 7; 2023: 1; 2024: 0; 2025: 0; 2026: 1.
17 papers.
Sort:
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
- 2022Graph neural networks for materials science and chemistrycited by 182
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
- 2021Reconstruction for Powerful Graph Representationscited by 65
- 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB filescited by 59
- 2022Ordered Subgraph Aggregation Networkscited by 57
- 2021Autobahn: Automorphism-based Graph Neural Netscited by 39
- 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
- 2021Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotationscited by 29
- 2022A graph representation of molecular ensembles for polymer property predictioncited by 20
- 2022Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquidscited by 14
- 2022Scalable Fragment-Based 3D Molecular Design with Reinforcement Learningcited by 11
5 more
- 2021Motif Graph Neural Networkcited by 10
- 2022Graph Machine Learning for Design of High-Octane Fuelscited by 6
- 2021Implementing graph neural networks with TensorFlow-Kerascited by 3
- 2026Learning Molecular Chirality via Chiral Determinant Kernelscited by 2
- 2021Image-Like Graph Representations for Improved Molecular Property Predictioncited by 0
- 2026Learning Molecular Chirality via Chiral Determinant Kernels7 Feb 2026
- 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files9 May 2023
- 2022Graph neural networks for materials science and chemistry5 Aug 2022
- 2022Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquids23 Jun 2022
- 2022Ordered Subgraph Aggregation Networks22 Jun 2022
- 2022Graph Machine Learning for Design of High-Octane Fuels1 Jun 2022
- 2022A graph representation of molecular ensembles for polymer property prediction17 May 2022
- 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks25 Mar 2022
- 2022Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning1 Feb 2022
- 2021Motif Graph Neural Network30 Dec 2021
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributions6 Dec 2021
- 2021Image-Like Graph Representations for Improved Molecular Property Prediction20 Nov 2021
5 more
- 2021Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations8 Oct 2021
- 2021Reconstruction for Powerful Graph Representations1 Oct 2021
- 2021GemNet: Universal Directional Graph Neural Networks for Molecules2 Jun 2021
- 2021Implementing graph neural networks with TensorFlow-Keras7 Mar 2021
- 2021Autobahn: Automorphism-based Graph Neural Nets2 Mar 2021
- 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
- 2022Graph neural networks for materials science and chemistrycited by 182
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
- 2021Reconstruction for Powerful Graph Representationscited by 65
- 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB filescited by 59
- 2022Ordered Subgraph Aggregation Networkscited by 57
- 2021Autobahn: Automorphism-based Graph Neural Netscited by 39
- 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
- 2021Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotationscited by 29
- 2022A graph representation of molecular ensembles for polymer property predictioncited by 20
- 2022Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquidscited by 14
- 2022Scalable Fragment-Based 3D Molecular Design with Reinforcement Learningcited by 11
12 most cited of 17 All 17 (JSON)
- 2026Learning Molecular Chirality via Chiral Determinant Kernels7 Feb 2026
- 2023Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files9 May 2023
- 2022Graph neural networks for materials science and chemistry5 Aug 2022
- 2022Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquids23 Jun 2022
- 2022Ordered Subgraph Aggregation Networks22 Jun 2022
- 2022Graph Machine Learning for Design of High-Octane Fuels1 Jun 2022
- 2022A graph representation of molecular ensembles for polymer property prediction17 May 2022
- 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks25 Mar 2022
- 2022Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning1 Feb 2022
- 2021Motif Graph Neural Network30 Dec 2021
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributions6 Dec 2021
- 2021Image-Like Graph Representations for Improved Molecular Property Prediction20 Nov 2021
12 newest of 17 All 17 (JSON)