On compressing frequent patterns Export

@article{citeulike:940966, abstract = {A major challenge in frequent-pattern mining is the sheer size of its mining results. To compress the frequent patterns, we propose to cluster frequent patterns with a tightness measure [delta] (called [delta]-cluster), and select a representative pattern for each cluster. The problem of finding a minimum set of representative patterns is shown NP-Hard. We develop two greedy methods, RPglobal and RPlocal. The former has the guaranteed compression bound but higher computational complexity. The latter sacrifices the theoretical bounds but is far more efficient. Our performance study shows that the compression quality using RPlocal is very close to RPglobal, and both can reduce the number of closed frequent patterns by almost two orders of magnitude. Furthermore, RPlocal mines even faster than FPClose [G. Grahne, J. Zhu, Efficiently using prefix-trees in mining frequent itemsets, in: Proc. IEEE ICDM Workshop on Frequent Itemset Mining Implementations (FIMI'03)], a very fast closed frequent-pattern mining method. We also show that RPglobal and RPlocal can be combined together to balance the quality and efficiency.}, author = {Xin, Dong and Han, Jiawei and Yan, Xifeng and Cheng, Hong}, booktitle = {Intelligent Data Mining}, citeulike-article-id = {940966}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.datak.2006.01.006}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B6TYX-4JD0FS3-4/2/f3b5bc289452c3a63e0468daf04da449}, doi = {10.1016/j.datak.2006.01.006}, journal = {Data \& Knowledge Engineering}, keywords = {freq\_sets}, month = {January}, number = {1}, pages = {5--29}, posted-at = {2006-11-12 23:30:29}, priority = {3}, title = {On compressing frequent patterns}, url = {http://dx.doi.org/10.1016/j.datak.2006.01.006}, volume = {60}, year = {2007} }

TY - JOUR ID - citeulike:940966 L3 - citeulike-article-id:940966 N2 - A major challenge in frequent-pattern mining is the sheer size of its mining results. To compress the frequent patterns, we propose to cluster frequent patterns with a tightness measure [delta] (called [delta]-cluster), and select a representative pattern for each cluster. The problem of finding a minimum set of representative patterns is shown NP-Hard. We develop two greedy methods, RPglobal and RPlocal. The former has the guaranteed compression bound but higher computational complexity. The latter sacrifices the theoretical bounds but is far more efficient. Our performance study shows that the compression quality using RPlocal is very close to RPglobal, and both can reduce the number of closed frequent patterns by almost two orders of magnitude. Furthermore, RPlocal mines even faster than FPClose [G. Grahne, J. Zhu, Efficiently using prefix-trees in mining frequent itemsets, in: Proc. IEEE ICDM Workshop on Frequent Itemset Mining Implementations (FIMI'03)], a very fast closed frequent-pattern mining method. We also show that RPglobal and RPlocal can be combined together to balance the quality and efficiency. IS - 1 JF - Data & Knowledge Engineering EP - 29 TI - On compressing frequent patterns VL - 60 T2 - Intelligent Data Mining SP - 5 KW - freq_sets AU - Xin, Dong AU - Han, Jiawei AU - Yan, Xifeng AU - Cheng, Hong PY - 2007/01// UR - http://dx.doi.org/10.1016/j.datak.2006.01.006 ER -