In several applications the information is naturally represented by graphs. Traditional approaches cope with graphical data structures using a preprocessing phase which transforms the graphs into a set of flat vectors. However, in this way, important topological information may be lost and the achieved results may heavily depend on the preprocessing stage. This paper presents a new neural model, called graph neural network (GNN), capable of directly processing graphs. GNNs extends recursive neural networks and can be applied on most of the practically useful kinds of graphs, including directed, undirected, labelled and cyclic graphs. A learning algorithm for GNNs is proposed and some experiments are discussed which assess the properties of the model.

Gori, M., G., M., Scarselli, F. (2005). A new model for learning in graph domains. In IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on Neural Networks (pp.729-734). New York : IEEE.

A new model for learning in graph domains

GORI, MARCO;SCARSELLI, FRANCO
2005-01-01

Abstract

In several applications the information is naturally represented by graphs. Traditional approaches cope with graphical data structures using a preprocessing phase which transforms the graphs into a set of flat vectors. However, in this way, important topological information may be lost and the achieved results may heavily depend on the preprocessing stage. This paper presents a new neural model, called graph neural network (GNN), capable of directly processing graphs. GNNs extends recursive neural networks and can be applied on most of the practically useful kinds of graphs, including directed, undirected, labelled and cyclic graphs. A learning algorithm for GNNs is proposed and some experiments are discussed which assess the properties of the model.
2005
0-7803-9048-2
Gori, M., G., M., Scarselli, F. (2005). A new model for learning in graph domains. In IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on Neural Networks (pp.729-734). New York : IEEE.
File in questo prodotto:
File Dimensione Formato  
ijcnn2005.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 128.43 kB
Formato Adobe PDF
128.43 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/19137
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo