Granular reducts of formal fuzzy contexts

Knowledge reduction is one of the key issues in knowledge discovery and data mining. During the construction of a concept lattice, it has been recognized that computational complexity is a major obstacle in deriving all the concept from a database. In order to improve the computational efficiency, it is necessary to preprocess the database and reduce its size as much as possible. Focusing on formal fuzzy contexts, we introduce in the paper the notions of granular consistent sets and granular reducts and propose granular reduct methods in the sense of reducing the attributes. With the proposed approaches, the attributes that are not essential to all the object concepts can be removed without loss of knowledge and, consequently, the computational complexity of constructing the concept lattice is reduced. Furthermore, the relationship between the granular reducts and the classification reducts in a formal fuzzy context is investigated.