A Novel Approach To Attribute Reduction In Formal Concept Lattices

The theory of concept lattice is an efficient tool for knowledge representation and knowledge discovery. One of the key problems of knowledge discovery is attribute reduction. This paper presents a novel approach to attribute reduction in formal concept lattices. The approach employs all the extents of the meet-irreducible elements in the lattice. Each of them determines a family of attribute sets common to the objects in the extent. By various combinations of minimal elements from each family we can produce reducts of the formal context. Furthermore, a related algorithm is developed, and an illustration example is employed to perform the reduction process of the proposed method.