Corpus ID: 126187239

Graph Element Networks: adaptive, structured computation and memory

@article{Alet2019GraphEN,
  title={Graph Element Networks: adaptive, structured computation and memory},
  author={Ferran Alet and Adarsh K. Jeewajee and Maria Bauz{\'a} and A. Rodr{\'i}guez and Tomas Lozano-Perez and L. Kaelbling},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.09019}
}
  • Ferran Alet, Adarsh K. Jeewajee, +3 authors L. Kaelbling
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. [...] Key Method We use GNNs as a computational substrate, and show that the locations of the nodes in space as well as their connectivity can be optimized to focus on the most complex parts of the space. Moreover, this representational strategy allows the learned input-output relationship to generalize over the size of the underlying space and run the same model at different levels…Expand Abstract
    11 Citations
    Neural Operator: Graph Kernel Network for Partial Differential Equations
    • 7
    • PDF
    Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
    • Highly Influenced
    • PDF
    A Multiscale Graph Convolutional Network Using Hierarchical Clustering
    • PDF
    Neural Relational Inference with Fast Modular Meta-learning
    • 14
    • PDF
    Multipole Graph Neural Operator for Parametric Partial Differential Equations
    • 3
    • PDF
    Graph Convolutional Neural Networks for Body Force Prediction
    • 2
    • PDF
    Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
    • 6
    • PDF
    Learning Mesh-Based Simulation with Graph Networks
    • 1
    • PDF

    References

    SHOWING 1-10 OF 71 REFERENCES
    Geometric Deep Learning: Going beyond Euclidean data
    • 1,227
    • PDF
    Flexible Neural Representation for Physics Prediction
    • 93
    • PDF
    The Graph Neural Network Model
    • 1,747
    • PDF
    A Compositional Object-Based Approach to Learning Physical Dynamics
    • 243
    • PDF
    GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
    • 24
    • PDF
    Graph Neural Networks: A Review of Methods and Applications
    • 622
    • PDF
    Graph Neural Networks for IceCube Signal Classification
    • 33
    • PDF
    Hybrid computing using a neural network with dynamic external memory
    • 921
    • PDF
    Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
    • 2,514
    • PDF
    Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
    • 771
    • PDF