## Office of the Vice-President Journal Articles

Journal Article

#### Department/Unit

Office of the Vice-President (Research and Development)

#### Title

The Graph Neural Network Model

#### 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 the graph domain. This GNN model, which can directly process most of the practically useful types of graphs, e.g. acyclic, cyclic, directed, un-directed, implements a transduction 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. Computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and demonstrate its generalization capability

2009

#### Journal Title

IEEE Transaction on Neural Networks

20

1

IEEE Press

81

102

1

#### Funder

Australian research Council

COinS