Selecting Important Concepts Using Weights

We present an approach that enables one to select a reasonable small number of possibly important formal concepts from the set of all formal concepts of a given input data. The problem to select a small number of concepts appears in applications of formal concept analysis when the number of all formal concepts of the input data is large. Namely, a user often asks for a list of "important concepts" in such case. In the present approach, attributes of the input data are assigned weights from which values of formal concepts are determined. Formal concepts with larger values are considered more important. The attribute weights are supposed to be set by the users. The approach is a continuation of our previous approaches that utilize background knowledge, i.e. additional knowledge of a user, to select parts of concept lattices. In addition to the approach, we present illustrative examples.

[1]  R. Mesiar,et al.  ”Aggregation Functions”, Cambridge University Press , 2008, 2008 6th International Symposium on Intelligent Systems and Informatics.

[2]  Vilém Vychodil,et al.  Formal Concept Analysis With Background Knowledge: Attribute Priorities , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  Rokia Missaoui,et al.  Restrictions on Concept Lattices for Pattern Management , 2010, CLA.

[4]  Olivier Ridoux,et al.  A Parameterized Algorithm to Explore Formal Contexts with a Taxonomy , 2008, Int. J. Found. Comput. Sci..

[5]  Vilém Vychodil,et al.  Formal Concept Analysis with Constraints by Closure Operators , 2006, ICCS.

[6]  Claudio Carpineto,et al.  Concept data analysis - theory and applications , 2004 .

[7]  Bernhard Ganter,et al.  Formal Concept Analysis: Mathematical Foundations , 1998 .

[8]  Pascal Hitzler,et al.  Conceptual Structures: Inspiration and Application, 14th International Conference on Conceptual Structures, ICCS 2006, Aalborg, Denmark, July 16-21, 2006, Proceedings , 2006, ICCS.

[9]  Sérgio M. Dias,et al.  Reducing the Size of Concept Lattices: The JBOS Approach , 2010, CLA.

[10]  Bernhard Ganter,et al.  Formal Concept Analysis , 2013 .

[11]  Bernhard Ganter,et al.  Attribute Exploration with Background Knowledge , 1999, Theor. Comput. Sci..

[12]  Lior Rokach,et al.  Data Mining And Knowledge Discovery Handbook , 2005 .

[13]  Radim Belohlávek,et al.  Formal Concept Analysis Constrained by Attribute-Dependency Formulas , 2005, ICFCA.

[14]  Jean-François Boulicaut,et al.  Constraint-based Data Mining , 2005, Data Mining and Knowledge Discovery Handbook.