Graphical-Based Learning Environments for Pattern Recognition

  • Franco Scarselli
  • Ah Chung Tsoi
  • Marco Gori
  • Markus Hagenbuchner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)


In this paper, we present a new neural network model, called graph neural network model, which is a generalization of two existing approaches, viz., the graph focused approach, and the node focused approach. The graph focused approach considers the mapping from a graph structure to a real vector, in which the mapping is independent of the particular node involved; while the node focused approach considers the mapping from a graph structure to a real vector, in which the mapping depends on the properties of the node involved. It is shown that the graph neural network model maintains some of the characteristics of the graph focused models and the node focused models respectively. A supervised learning algorithm is derived to estimate the parameters of the graph neural network model. Some experimental results are shown to validate the proposed learning algorithm, and demonstrate the generalization capability of the proposed model.


  1. 1.
    Brin, S., Page, L.: The anatomy of a large–scale hypertextual Web search engine. In: Proceedings of the 7th World Wide Web Conference (April 1998)Google Scholar
  2. 2.
    Diligenti, M., Gori, M., Maggini, M.: A learning algorithm for web page scoring systems. In: Proceedings of International Joint Conference on Artificial Intelligence (2003)Google Scholar
  3. 3.
    Frasconi, P., Gori, M., Sperduti, A.: A general framework for adaptive processing of data structures. IEEE Transactions on Neural Networks 9(5), 768–786 (1998)CrossRefGoogle Scholar
  4. 4.
    Caianiello, E.R.: International Summer School on Neural Networks. In: Giles, C.L., Gori, M. (eds.) IIASS-EMFCSC-School 1997. LNCS (LNAI), vol. 1387, Springer, Heidelberg (1998)Google Scholar
  5. 5.
    Hagenbuchner, M., Sperduti, A., Tsoi, A.C.: A self-organizing map for adaptive processing of structured data. IEEE Transactions on Neural Networks (2003)Google Scholar
  6. 6.
    Hagenbuchner, M., Tsoi, A.C., Sperduti, A.: A supervised self-organising map for structured data. In: Allinson, N., Yin, H., Allinson, L., Slack, J. (eds.) WSOM 2001 - Advances in Self-Organising Maps, June 2001, pp. 21–28. Springer, Heidelberg (2001)Google Scholar
  7. 7.
    Khamsi, M.A.: An Introduction to Metric Spaces and Fixed Point Theory. John Wiley & Sons, Chichester (2001)Google Scholar
  8. 8.
    Kleinberg, J.: Authoritative sources in a hyperlinked environment. Journal of the ACM 46(5), 604–632 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Scarselli, F., Tsoi, A.C., Gori, M., Hegenbuchner, M.: A new neural network approach to graph processing. Technical Report DII /04, Dipartimento di Ingeneria dell’Inforazione, University of Siena, Siena, Italy (2004)Google Scholar
  10. 10.
    Seneta, E.: Non–negative matrices and Markov chains, ch. 4, pp. 112–158. Springer, Heidelberg (1981)zbMATHGoogle Scholar
  11. 11.
    Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks 8, 429–459 (1997)CrossRefGoogle Scholar
  12. 12.
    Tsoi, A.C., Morini, G., Scarselli, F., Hagenbuchner, Maggini, M.M.: Adaptive ranking of web pages. In: Proceedings of the 12th WWW Conference, Budapest, Hungary (May 2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Franco Scarselli
    • 1
  • Ah Chung Tsoi
    • 3
  • Marco Gori
    • 1
  • Markus Hagenbuchner
    • 2
  1. 1.Dipartimento di Ingegneria dell’InformazioneUniversity of SienaSienaItaly
  2. 2.Faculty of InformaticsUniversity of WollonongWollongongAustralia
  3. 3.Executive Director, Mathematics, Informatics & Comunication–ScienceAustralian Research CouncilCamberraAustralia

Personalised recommendations