KES2007: Special Session on PATTERN RECOGNITION IN GRAPHICAL DOMAINS

Topics

Traditional machine learning applications usually cope with graphs by a preprocessing procedure that transforms structured data to simpler representations. This approach relies on what is called the "feature extraction" process, but it turns out to be quite unnatural for several situations where data are intrinsically organized as graphs, i.e. relationships exist among atomic sub-entities. Unfortunately, valuable information may be lost during the preprocessing and, as a consequence, classical methods may suffer from poor performance and generalization.
Therefore, recursive or nested representations, as opposed to "flat" attribute-value data organizations, seem to be more adequate for many relevant problems arising from chemistry, bioinformatics, and the World Wide Web. Recent studies on statistical pattern recognition and neural networks show possible directions to exploit structural information in problems which are inherently of sub-symbolic nature.
This special session is intended to propose a critical re-thinking of the classic learning approaches and to investigate on possible new methodologies and applications of pattern recognition in graphical domains.

The scope of this session is, but not limited to:

Paper submission

Authors are encouraged to submit high quality, original work that has neither appeared in, nor is under consideration by, other conferences/journals. All submissions will be refereed by experts in the field based on originality, significance, and clarity. The conference preceedings will be published by Springer-Verlag in Lecture Notes in AI as part of the LNCS/LNAI series. When formatting papers - that must be no more than eight (8) pages long, including figures and bibliography - please refer to the Springer-Verlag site and strictly follow the instructions for LNCS authors (http://www.springer.de/comp/lncs/authors.html).

Special Issue on Neurocomputing

Authors of selected manuscripts will be also invited to submit an extended version of their paper for publication in a special issue of the Neurocomputing Journal, published by Elsevier Science (http://www.elsevier.nl/locate/neucom).

Important Dates

Deadline for paper submission: March 10th 2007

Notification of acceptance: April 10th 2007

Camera-ready papers: May 1st 2007

Organized by:

Chairs

Monica Bianchini - University of Siena, Italy

Franco Scarselli - University of Siena, Italy

Program Committee

Markus Hagenbuchner - University of Wollongong, Australia

Barbara Hammer - Clausthal University of Technology, Germany

Simone Marinai - University of Florence, Italy

Lionel Prevost - Université Pierre et Marie Curie, France

Jan Ramon - K. U. Leuven, Belgium

Friedhelm Schwenker - University of Ulm, Germany

Alessandro Sperduti - University of Padua, Italy

Peter Tino - University of Birmingham, United Kingdom

More detailed information and the electronic submission form are available at http://kes2007.kesinternational.org/submission.php

	KES2007 11th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems in conjunctions with WIRN2007 17th Italian Workshop on Neural Network Vietri sul Mare, Italy 12, 13 and 14 September 2007

	Call for Papers: Special Session on PATTERN RECOGNITION IN GRAPHICAL DOMAINS

	Topics Traditional machine learning applications usually cope with graphs by a preprocessing procedure that transforms structured data to simpler representations. This approach relies on what is called the "feature extraction" process, but it turns out to be quite unnatural for several situations where data are intrinsically organized as graphs, i.e. relationships exist among atomic sub-entities. Unfortunately, valuable information may be lost during the preprocessing and, as a consequence, classical methods may suffer from poor performance and generalization. Therefore, recursive or nested representations, as opposed to "flat" attribute-value data organizations, seem to be more adequate for many relevant problems arising from chemistry, bioinformatics, and the World Wide Web. Recent studies on statistical pattern recognition and neural networks show possible directions to exploit structural information in problems which are inherently of sub-symbolic nature. This special session is intended to propose a critical re-thinking of the classic learning approaches and to investigate on possible new methodologies and applications of pattern recognition in graphical domains. The scope of this session is, but not limited to: Neural Network Models for Graphs Support Vector Machines and Kernel Methods for Graphs Probabilistic Models for Graphs Statistical Relational Learning Pattern Recognition Applications Involving Graphical Data Paper submission Authors are encouraged to submit high quality, original work that has neither appeared in, nor is under consideration by, other conferences/journals. All submissions will be refereed by experts in the field based on originality, significance, and clarity. The conference preceedings will be published by Springer-Verlag in Lecture Notes in AI as part of the LNCS/LNAI series. When formatting papers - that must be no more than eight (8) pages long, including figures and bibliography - please refer to the Springer-Verlag site and strictly follow the instructions for LNCS authors (http://www.springer.de/comp/lncs/authors.html). Special Issue on Neurocomputing Authors of selected manuscripts will be also invited to submit an extended version of their paper for publication in a special issue of the Neurocomputing Journal, published by Elsevier Science (http://www.elsevier.nl/locate/neucom). Important Dates Deadline for paper submission: March 10th 2007 Notification of acceptance: April 10th 2007 Camera-ready papers: May 1st 2007 Organized by: Chairs Monica Bianchini - University of Siena, Italy Franco Scarselli - University of Siena, Italy Program Committee Markus Hagenbuchner - University of Wollongong, Australia Barbara Hammer - Clausthal University of Technology, Germany Simone Marinai - University of Florence, Italy Lionel Prevost - Université Pierre et Marie Curie, France Jan Ramon - K. U. Leuven, Belgium Friedhelm Schwenker - University of Ulm, Germany Alessandro Sperduti - University of Padua, Italy Peter Tino - University of Birmingham, United Kingdom More detailed information and the electronic submission form are available at http://kes2007.kesinternational.org/submission.php