Abstract: Many approaches are used to develop efficient algorithms for mining frequent patterns. Recent studies on frequent itemset mining algorithms resulted in significant performance improvements. However, if the minimum support is set to low, or the data is highly correlated, the number of frequent itemsets itself can be prohibitively large. To overcome this problem, several proposals have been made to construct a concise representation of the frequent itemsets, instead of mining all frequent itemsets. This survey paper illustrates the importance of FP-growth based algorithms for mining representative pattern sets. It also discusses that the number of representative pattern sets can be much smaller than the total number of frequent patterns; all the frequent patterns and their support can be recovered from the set of representative patterns. That is, the representative pattern sets are used to best approximate all frequent patterns.

Keywords: Depth-First strategy, FP- growth, frequent itemset, closed itemset, Representative Pattern set.