Computational Capabilities of Graph Neural Networks

@article{Scarselli2009ComputationalCO,
  title={Computational Capabilities of Graph Neural Networks},
  author={F. Scarselli and M. Gori and A. Tsoi and M. Hagenbuchner and G. Monfardini},
  journal={IEEE Transactions on Neural Networks},
  year={2009},
  volume={20},
  pages={81-102}
}
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
103 Citations
The Graph Neural Network Model
  • 1,910
  • PDF
How Powerful are Graph Neural Networks?
  • 1,133
  • PDF
Generalization and Representational Limits of Graph Neural Networks
  • 39
  • PDF
Graph Neural Networks: A Review of Methods and Applications
  • 728
  • PDF
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
  • 270
  • PDF
Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
  • 3
  • PDF
Recursive Neural Networks for Density Estimation Over Generalized Random Graphs
  • 8
  • Highly Influenced
iPool - Information-based Pooling in Hierarchical Graph Neural Networks
  • 4
  • PDF
Fast Haar Transforms for Graph Neural Networks
  • 10
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 69 REFERENCES
The Graph Neural Network Model
  • 1,910
  • PDF
A Comparison between Recursive Neural Networks and Graph Neural Networks
  • 30
  • PDF
A new model for learning in graph domains
  • 580
A general framework for adaptive processing of data structures
  • 435
  • PDF
Supervised neural networks for the classification of structures
  • 405
Recursive neural networks for processing graphs with labelled edges: theory and applications
  • 46
  • PDF
A self-organizing map for adaptive processing of structured data
  • 199
  • PDF
Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results
  • 399
  • PDF
...
1
2
3
4
5
...