M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length-decreasing support constraint. Proceedings of ICDM'01, pages 505-- 512, 2001.  Home/Search   Document Details and Download   Summary   Related Articles   Check

No context found.

M. Seno, G. Karypis. LPMiner: An Algorithm for Finding Frequent Itemsets Using Length-Decreasing Support Constraint, ICDM'01.

No context found.

M. Seno, G. Karypis, LPMiner: An Algorithm for Finding Frequent Itemsets Using Length-Decreasing Support Constraint, ICDM'01, Nov. 2001.

No context found.

M. Seno, G. Karypis, LPMiner: An Algorithm for Finding Frequent Itemsets Using Length-Decreasing Support Constraint, ICDM'01, Nov. 2001.

....into small and independent chunks and use a vertical database format that allows them to determine the frequency by computing set intersections. More recently, a set of database projection based methods has been developed that significantly reduces the complexity of finding frequent patterns [1, 9, 21, 23, 24]. The key idea behind these approaches is to find the patterns by growing them one item at a time, and simultaneously partitioning (i.e. projecting) the original database into pattern specific subdatabases (which in general overlap) The process of pattern growth and database projection is ....

Masakazu Seno and George Karypis. Lpminer: An algorithm for finding frequent itemsets using lengthdecreasing support constraint. In IEEE International Conference on Data Mining, 2001. Also available as a UMN-CS technical report, TR# 01-026.

....into small and independent chunks and use a vertical database format that allows them to determine the frequency by computing set intersections. More recently, a set of database projection based methods has been developed that significantly reduces the complexity of finding frequent patterns [1, 9, 21, 23, 24]. The key idea behind these approaches is to find the patterns by growing them one item at a time, and simultaneously partitioning (i.e. projecting) the original database into pattern specific subdatabases (which in general overlap) The process of pattern growth and database projection is ....

Masakazu Seno and George Karypis. Lpminer: An algorithm for finding frequent itemsets using lengthdecreasing support constraint. In IEEE International Conference on Data Mining, 2001. Also available as a UMN-CS technical report, TR# 01-026.

....an algorithm that finds all the frequent patterns whose support decreases as a function of their length. Developing such an algorithm is particularly challenging because the downward closure property of the constant support constraint cannot be used to prune short infrequent patterns. Recently [9], we introduced the problem of finding frequent itemsets whose support satisfies a non increasing function of their length. An itemset is frequent only if its support is greater than or equal to the minimum support value determined by the length of the itemset. We identified a property that an ....

....of short infrequent itemsets if these itemsets are maximal. As for the frequent sequential pattern mining, even the problem of finding maximal patterns has not been addressed mainly due to the high complexity of the problem. Recently, we introduced the idea of length decreasing support constraint [9] that helps us to find long itemsets with low support as well as short itemsets with high support. A length decreasing support constraint is given as a function of the itemset length #### such that ### # # # ### # # for any # # ## # satisfying # # # . The idea of introducing this kind of ....

[Article contains additional citation context not shown here]

M. Seno and G. Karypis. Lpminer: An algorithm for finding frequent itemsets using length-decreasing support constraint. In 1st IEEE Conference on Data Mining, 2001.

....the performance of FSG on datasets with di#erent characteristics we developed a synthetic dataset generator. The design of our generator was inspired by the synthetic transaction generator developed by the Quest group at IBM and used extensively to evaluate algorithms that find frequent itemsets [2, 1, 15, 22]. In the reminder of this section we first describe the synthetic graph generator followed by a detailed experimental evaluation of FSG on a wide range of synthetically generated datasets. 6.3.1 Dataset Generator Our synthetic dataset generator produces a database of graph transactions whose ....

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length decreasing support constraint. In Proc. of the 1st IEEE International Conference on Data Mining (ICDM), November 2001.

....14. This non linear relation between the time complexity and the size of the transaction is due to the fact that the algorithm needs to explore a much higher search space, and is consistent with the time increases for other pattern discovery algorithms, such as those for finding frequent itemsets [12] and sequential patterns [13] Nevertheless, gFSG is able to mine the largest dataset with a support of 0.25 in less than two hours. Also, comparing the scale invariant with the scale variant experiments, we can see that as before, finding the scale variant patterns is faster by about a factor of ....

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length decreasing support constraint. In Proc. of the 1st IEEE International Conference on Data Mining (ICDM), November 2001. 16

....the performance of FSG on datasets with different characteristics we developed a synthetic dataset generator. The design of our generator was inspired by the synthetic transaction generator developed by the Quest group at IBM and used extensively to evaluate algorithms that find frequent itemsets [2, 1, 15, 22]. In the reminder of this section we first describe the synthetic graph generator followed by a detailed experimental evaluation of FSG on a wide range of synthetically generated datasets. 6.3.1 Dataset Generator Our synthetic dataset generator produces a database of graph transactions whose ....

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length decreasing support constraint. In Proc. of the 1st IEEE International Conference on Data Mining (ICDM), November 2001.

....14. This non linear relation between the time complexity and the size of the transaction is due to the fact that the algorithm needs to explore a much higher search space, and is consistent with the time increases for other pattern discovery algorithms, such as those for finding frequent itemsets [12] and sequential patterns [13] Nevertheless, gFSG is able to mine the largest dataset with a support of 0.25 in less than two hours. Also, comparing the scale invariant with the scale variant experiments, we can see that as before, finding the scale variant patterns is faster by about a factor of ....

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length decreasing support constraint. In Proc. of the 1st IEEE International Conference on Data Mining (ICDM), November 2001. 16

....an algorithm that finds all the frequent patterns whose support decreases as a function of their length. Developing such an algorithm is particularly challenging because the downward closure property of the constant support constraint cannot be used to prune short infrequent patterns. Recently [9], we introduced the problem of finding frequent itemsets whose support satisfies a non increasing function of their length. An itemset is frequent only if its support is greater than or equal to the minimum support value determined by the length of the itemset. We identified a property that an ....

....of short infrequent itemsets if these itemsets are maximal. As for the frequent sequential pattern mining, even the problem of finding maximal patterns has not been addressed mainly due to the high complexity of the problem. Recently, we introduced the idea of length decreasing support constraint [9] that helps us to find long itemsets with low support as well as short itemsets with high support. A length decreasing support constraint is given as a function of the itemset length f(l) such that f(l a ) f(l b ) for any l a ; l b satisfying l a l b . The idea of introducing this kind of ....

[Article contains additional citation context not shown here]

M. Seno and G. Karypis. Lpminer: An algorithm for finding frequent itemsets using length-decreasing support constraint. In 1st IEEE Conference on Data Mining, 2001.

....association rules, the field of associating rules and especially its sub field of frequent itemset generation has seen a great deal of research activity. The extensive research in this field has led to the development of efficient techniques for generating, storing and pruning frequent itemsets [SK01, HPY00, AAP00, Zak00] These advances accompanied by growth in the computing power has made the task of frequent itemsets generation much more manageable, than in the past. As a result, we have witnessed an increased interest in developing schemes that use frequently occurring itemsets to aid in ....

....The Frequent Itemset Discovery Algorithm, henceforth referred as FIDA, returns a list of itemsets which occur frequently in the dataset. Each itemset represents a composite feature that is a conjunction of all the attribute values (items) making up that itemset. In our procedure we use LPMiner [SK01] as our FIDA. The notion of frequent, i.e, what composite feature is considered as frequent is controlled by a user defined parameter to the FIDA called support threshold. All the composite features (itemsets) generated by FIDA have a support above the support threshold. Support for a composite ....

Masakazu Seno and George Karypis. Lpminer: An algorithm for finding frequent itemsets using lengthdecreasing support constraint. In IEEE International Conference on Data Mining, 2001. Also available as a UMN-CS technical report, TR# 01-026.

No context found.

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length-decreasing support constraint. Proceedings of ICDM'01, pages 505-- 512, 2001.

No context found.

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length-decreasing support constraint. Proceedings of ICDM'01, pages 505-- 512, 2001.

No context found.

M. Seno and G. Karypis. LPMiner: An algorithm for finding frequent itemsets using length-decreasing support constraint. Proceedings of ICDM'01, pages 505-- 512, 2001.

No context found.

M. Seno and G. Karypis. Lpminer: An algorithm for finding frequent itemsets using length-decreasing support constraint. In Proc. of the 1st IEEE Conf. on Data Mining, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC