Neural computation, social networks, and topological spectra
Theoretical Computer Science
Neural Networks - Special issue on neural networks and kernel methods for structured domains
A Neural Network Approach to Similarity Learning
ANNPR '08 Proceedings of the 3rd IAPR workshop on Artificial Neural Networks in Pattern Recognition
The graph neural network model
IEEE Transactions on Neural Networks
Neural network for graphs: a contextual constructive approach
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Recursive neural networks are conceived for processing graphs and extend the well-known recurrent model for processing sequences. In Frasconi et al. (1998), recursive neural networks can deal only with directed ordered acyclic graphs (DOAGs), in which the children of any given node are ordered. While this assumption is reasonable in some applications, it introduces unnecessary constraints in others. In this paper, it is shown that the constraint on the ordering can be relaxed by using an appropriate weight sharing, that guarantees the independence of the network output with respect to the permutations of the arcs leaving from each node. The method can be used with graphs having low connectivity and, in particular, few outcoming arcs. Some theoretical properties of the proposed architecture are given. They guarantee that the approximation capabilities are maintained, despite the weight sharing