Corpus ID: 211842237

Directional Message Passing for Molecular Graphs

@article{Klicpera2020DirectionalMP,
  title={Directional Message Passing for Molecular Graphs},
  author={Johannes Klicpera and Janek Gross and Stephan G{\"u}nnemann},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.03123}
}
  • Johannes Klicpera, Janek Gross, Stephan Günnemann
  • Published 2020
  • Mathematics, Computer Science, Physics
  • ArXiv
  • Graph neural networks have recently achieved great successes in predicting quantum mechanical properties of molecules. These models represent a molecule as a graph using only the distance between atoms (nodes) and not the spatial direction from one atom to another. However, directional information plays a central role in empirical potentials for molecules, e.g. in angular potentials. To alleviate this limitation we propose directional message passing, in which we embed the messages passed… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 12 CITATIONS

    Neural Message Passing on High Order Paths

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Generalization and Representational Limits of Graph Neural Networks

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Isometric Transformation Invariant and Equivariant Graph Convolutional Networks

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Graph-Aware Transformer: Is Attention All Graphs Need?

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Hierarchical Inter-Message Passing for Learning on Molecular Graphs

    VIEW 4 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Distance-Geometric Graph Convolutional Network (DG-GCN)

    VIEW 1 EXCERPT
    CITES BACKGROUND

    GROVER: Self-supervised Message Passing Transformer on Large-scale Molecular Data

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 50 REFERENCES

    Cormorant: Covariant Molecular Neural Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Provably Powerful Graph Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL