A new model for learning in graph domains

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.Published 5 January 2006

Marco Gori, Gabriele Monfardini, Franco Scarselli

DOI10.1109/ijcnn.2005.1555942

Citations1,846

TL;DR

A new neural model, called graph neural network (GNN), capable of directly processing graphs, which extends recursive neural networks and can be applied on most of the practically useful kinds of graphs, including directed, undirected, labelled and cyclic graphs.

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.

Keywords

Computer Science

Physical Review LettersGeneralization of back-propagation to recurrent neural networks

951 Citations1987Fernando J. Pineda

An adaptive neural network with asymmetric connections is introduced that bears a resemblance to the master/slave network of Lapedes and Farber but it is architecturally simpler.

IEEE Transactions on Neural NetworksSupervised neural networks for the classification of structures

643 Citations1997Alessandro Sperduti, Antonina Starita

It is shown that neural networks can, in fact, represent and classify structured patterns and all the supervised networks developed for the classification of sequences can, on the whole, be generalized to structures.

IEEE Transactions on Neural NetworksA general framework for adaptive processing of data structures

474 Citations1998Paolo Frasconi, Marco Gori +1 more

The framework described in this paper is an attempt to unify adaptive models like artificial neural nets and belief nets for the problem of processing structured information, where relations between data variables are expressed by directed acyclic graphs, where both numerical and categorical values coexist.

An Introduction to Metric Spaces and Fixed Point Theory

384 Citations2001Mohamed A. Khamsi, W. A. Kirk

Lecture notes in computer scienceLogo recognition by recursive neural networks

65 Citations1998Enrico Francesconi, Paolo Frasconi +5 more

This paper proposes recognizing logo images by using an adaptive model referred to as recursive artificial neural network, which contains the topological structured information of logo and continuous values pertaining to each contour node in the contour-tree representation of logo image.

A recursive neural network model for processing directed acyclic graphs with labeled edges

20 Citations2004Marco Gori, Marco Maggini +1 more

A new recursive neural network model is proposed which allows us to process directed acyclic graphs (DAGs) with labeled edges, relaxing the positional constraint and the correlated maximum outdegree limit and the results show that the new RNN model outperforms the standard RNN architecture, also allowing us to use a smaller number of free parameters.

Face Spotting in Color Images using Recursive Neural Networks

17 Citations2003Monica Bianchini, Paolo Mazzoni +2 more

This paper proposes a novel approach to the solution of the face localization problem using recursive neural networks that assumes a graph–based representation of images that combines structural and sub–symbolic visual features.

Recursive processing of cyclic graphs

15 Citations2003Monica Bianchini, Marco Gori +1 more

A methodology is proposed which allows us to map any cyclic directed graph into a "recursive-equivalent" tree, and the computational power of recursive networks is definitely established, also clarifying the underlying limitations of the model.

Lecture notes in computer scienceInductive inference of tree automata by recursive neural networks

5 Citations1997Paolo Frasconi, M. Gori +3 more

Recurrent neural networks are powerful learning machines capable of processing sequences but can conveniently be used to process also general data structures like trees and graphs, which opens the doors to a number of new very interesting applications previously unexplored.