Corpus ID: 219792342

Temporal Graph Networks for Deep Learning on Dynamic Graphs

@article{Rossi2020TemporalGN,
  title={Temporal Graph Networks for Deep Learning on Dynamic Graphs},
  author={E. Rossi and Ben Chamberlain and F. Frasca and D. Eynard and Federico Monti and M. Bronstein},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.10637}
}
  • E. Rossi, Ben Chamberlain, +3 authors M. Bronstein
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Graph Neural Networks (GNNs) have become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 78 REFERENCES
    Streaming Graph Neural Networks
    15
    DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks
    13
    EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
    47
    Dynamic Graph Convolutional Networks
    43
    Representation Learning for Dynamic Graphs: A Survey
    4
    Structured Sequence Modeling with Graph Convolutional Recurrent Networks
    114
    DynGEM: Deep Embedding Method for Dynamic Graphs
    89
    Learning Graph Dynamics using Deep Neural Networks
    14
    evolve2vec: Learning Network Representations Using Temporal Unfolding
    3
    Dynamic Network Embeddings: From Random Walks to Temporal Random Walks
    16