Computational Capabilities of Graph Neural Networks

@article{Scarselli2009ComputationalCO,
  title={Computational Capabilities of Graph Neural Networks},
  author={Franco Scarselli and Marco Gori and Ah Chung Tsoi and Markus Hagenbuchner and Gabriele Monfardini},
  journal={IEEE Transactions on Neural Networks},
  year={2009},
  volume={20},
  pages={81-102}
}
Highlight Information
In this paper, we will consider the approximation properties of a recently introduced neural network model called graph neural network (GNN), which can be used to process-structured data inputs, e.g., acyclic graphs, cyclic graphs, and directed or undirected graphs. [...] Key Result Some experimental examples are used to show the computational capabilities of the proposed model.Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 58 CITATIONS

Recursive Neural Networks for Density Estimation Over Generalized Random Graphs

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Impact sensitive ranking of structured documents

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

What Can Neural Networks Reason About?

VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Relational inductive biases, deep learning, and graph networks

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Graph Neural Networks and Boolean Satisfiability

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Unfolding Trees & Symmetrically-Associated Graphs

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Link-based web spam detection using weight properties

VIEW 1 EXCERPT
CITES METHODS
HIGHLY INFLUENCED

Tprank: contend with Web Spam using Trust Propagation

VIEW 1 EXCERPT
CITES METHODS
HIGHLY INFLUENCED

Network attacks and securing streaming content

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2020

CITATION STATISTICS

  • 10 Highly Influenced Citations

  • Averaged 8 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

The Graph Neural Network Model

VIEW 20 EXCERPTS

Approximation capabilities of folding networks

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Neural networks and principal component analysis: Learning from examples without local minima

VIEW 15 EXCERPTS
HIGHLY INFLUENTIAL

Supervised neural networks for the classification of structures

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A Comparison between Recursive Neural Networks and Graph Neural Networks

VIEW 1 EXCERPT

Recursive processing of cyclic graphs

VIEW 1 EXCERPT