SCSSE Seminar

Title: Graph Neural Networks
Speaker: Prof Franco Scarselli

Day:14/06/2007

Abstract: "Most of nowadays learning schemes neglect the importance of relationships amongst atomic entities in (e.g. graph) structured data. On the opposite, there are plenty of learning tasks from, amongst others, chemistry, biology, pattern recognition, and data mining that can take advantage from structural representations and from a systematic exploitation of data relationships. This seminar presents a new machine learning approach, called Graph Neural Network (GNN), where the input data is represented by graphs: the nodes denote concepts or objects, while the edges represent their relationships. GNNs can process general kinds of graphs, directed, undirected, cyclic, acyclic, positional and non positional graphs. It has been proved that GNNs have a universal approximation property and can approximate most of the practically useful functions on graphs. We also report experimental results obtained on some applications." BIOGRAPHY: Franco Scarselli received the Laurea degree in computer science from the University of Pisa, Italy, and the Ph.D. degree in computer and automation engineering from the University of Florence, Italy, in 1989 and 1995, respectively. In 1990 and 1991, Prof Scarselli was with the Computer Science Department at the University of Pisa, where he was supported by Consorzio Pisa Ricerche and took part to the Oikos project. He then moved to the Systems and Computer Department at the University of Florence, where he received his Ph.D and a postdoc. He also spent some months as a visiting student at the Department of Electrical and Computer Engineering of the University of Queensland, Australia. Since 1999, he has been at the Department of Computer Engineering at the University of Siena, and is currently holding a professorial role. His research interests include machine learning algorithms, adaptive processing of data structures, machine learning for web applications, neural networks, and approximation theory.