Skip to main content
placeholder image

The graph neural network model

Journal Article


Download full-text (Open Access)

Abstract


  • Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, undirected, implements a function $\tau(\BG,n)\in\R^m$ that maps a graph $\BG$ and one of its nodes $n$ into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

Authors


  •   Scarselli, Franco (external author)
  •   Gori, Marco (external author)
  •   Tsoi, Ah Chung
  •   Hagenbuchner, M.
  •   Monfardini, Gabriele (external author)

Publication Date


  • 2009

Citation


  • Scarselli, F., Gori, M., Tsoi, A., Hagenbuchner, M. & Monfardini, G. (2009). The graph neural network model. IEEE Transactions on Neural Networks, 20 (1), 61-80.

Scopus Eid


  • 2-s2.0-58649113008

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=10501&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/3165

Number Of Pages


  • 19

Start Page


  • 61

End Page


  • 80

Volume


  • 20

Issue


  • 1

Abstract


  • Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, undirected, implements a function $\tau(\BG,n)\in\R^m$ that maps a graph $\BG$ and one of its nodes $n$ into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

Authors


  •   Scarselli, Franco (external author)
  •   Gori, Marco (external author)
  •   Tsoi, Ah Chung
  •   Hagenbuchner, M.
  •   Monfardini, Gabriele (external author)

Publication Date


  • 2009

Citation


  • Scarselli, F., Gori, M., Tsoi, A., Hagenbuchner, M. & Monfardini, G. (2009). The graph neural network model. IEEE Transactions on Neural Networks, 20 (1), 61-80.

Scopus Eid


  • 2-s2.0-58649113008

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=10501&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/3165

Number Of Pages


  • 19

Start Page


  • 61

End Page


  • 80

Volume


  • 20

Issue


  • 1