Incremental mining of generator representation using border sets

Incremental frequent itemset mining refers to the maintenance and utilization of the knowledge discovered in the previous mining operations for later frequent itemset mining. This paper describes an incremental algorithm for maintaining the generator representation in dynamic datasets. The generator representation is a kind of lossless, concise representation of the set of frequent itemsets. It may be orders of magnitude smaller than the set of frequent itemsets. Furthermore, the algorithm utilizes a novel optimization based on generator borders for the first time in the literature. Generator borders are the borderline between frequent generators and other itemsets. New frequent generators can be generated through monitoring them. Extensive Experiments show that this algorithm is more efficient than previous solutions.