Corpus ID: 59158826

Typed Graph Networks

@article{Avelar2019TypedGN,
  title={Typed Graph Networks},
  author={Pedro H. C. Avelar and H. Lemos and Marcelo O. R. Prates and M. Gori and L. Lamb},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.07984}
}
  • Pedro H. C. Avelar, H. Lemos, +2 authors L. Lamb
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Recently, the deep learning community has given growing attention to neural architectures engineered to learn problems in relational domains. Convolutional Neural Networks employ parameter sharing over the image domain, tying the weights of neural connections on a grid topology and thus enforcing the learning of a number of convolutional kernels. By instantiating trainable neural modules and assembling them in varied configurations (apart from grids), one can enforce parameter sharing over… CONTINUE READING
    Learning to solve NP-complete problems
    • 5
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    Gated Graph Sequence Neural Networks
    • 1,075
    • PDF
    Multitask Learning on Graph Neural Networks - Learning Multiple Graph Centrality Measures with a Unified Network
    • 2
    • PDF
    The Graph Neural Network Model
    • 1,442
    • PDF
    Relational inductive biases, deep learning, and graph networks
    • 727
    • Highly Influential
    • PDF
    A simple neural network module for relational reasoning
    • 777
    • PDF
    Recurrent Relational Networks
    • 62
    • PDF
    A new model for learning in graph domains
    • 463
    Neural Message Passing for Quantum Chemistry
    • 1,332
    • PDF
    Recurrent Relational Networks for Complex Relational Reasoning
    • 23
    Deep Residual Learning for Image Recognition
    • 50,397
    • PDF