The common approaches to association rule mining focus on generating rule by using correlation among data and finding frequent occurring patterns. The main technique uses support and confidence measures for generating rules. There are few other approaches that have already been induced to improve association rule mining. The purpose of this paper is to review the existing approaches based of fuzzy and its variants and extensions namely Rough Set, Vague Set and Soft Set and their combinations that have been used to increase the effectiveness of association rule mining techniques dealt with the uncertainty, approximation, vagueness, and imprecision theories.