Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing framework, but they can be applied to different input domains. RNNs require the input graphs to be directed and acyclic, whereas GNNs can process any kind of graphs. The aim of this paper consists in understanding whether such a difference affects the behaviour of the models on a real application. An experimental comparison on an image classification problem is presented, showing that GNNs outperforms RNNs. Moreover the main differences between the models are also discussed w.r.t. their input domains, their approximation capabilities and their learning algorithms.

DI MASSA, V., Monfardini, G., Sarti, L., Scarselli, F., Maggini, M., Gori, M. (2006). A Comparison between Recursive Neural Networks and Graph Neural Networks. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2006) (pp.778-785) [10.1109/IJCNN.2006.246763].

A Comparison between Recursive Neural Networks and Graph Neural Networks

DI MASSA, VINCENZO;MONFARDINI, GABRIELE;SARTI, LORENZO;SCARSELLI, FRANCO;MAGGINI, MARCO;GORI, MARCO
2006-01-01

Abstract

Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing framework, but they can be applied to different input domains. RNNs require the input graphs to be directed and acyclic, whereas GNNs can process any kind of graphs. The aim of this paper consists in understanding whether such a difference affects the behaviour of the models on a real application. An experimental comparison on an image classification problem is presented, showing that GNNs outperforms RNNs. Moreover the main differences between the models are also discussed w.r.t. their input domains, their approximation capabilities and their learning algorithms.
0780394909
DI MASSA, V., Monfardini, G., Sarti, L., Scarselli, F., Maggini, M., Gori, M. (2006). A Comparison between Recursive Neural Networks and Graph Neural Networks. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2006) (pp.778-785) [10.1109/IJCNN.2006.246763].
File in questo prodotto:
File Dimensione Formato  
IJCNN06.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 250.78 kB
Formato Adobe PDF
250.78 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/11365/35875
 Attenzione

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