Inverse frequent itemset mining (IFM) consists of generating artificial transactional databases reflecting patterns of real ones, in particular, satisfying given frequency constraints on the itemsets. An extension of IFM called many-sorted IFM, is introduced where the schemes for the datasets to be generated are those typical of Big Tables, as required in emerging big data applications, e.g., social network analytics.
This document was originally published in AMW 2016 - Proceedings of the 10th Alberto Mendelzon International Workshop on Foundations of Data Management by CEUR-WS. Copyright restrictions may apply.
Saccà, Domenico; Serra, Edoardo; and Piccolo, Antonio. (2016). "Multi-Sorted Inverse Frequent Itemsets Mining: On-Going Research". AMW 2016: Proceedings of the 10th Alberto Mendelzon International Workshop on Foundations of Data Management, 1644.