@article{ivncsy2006frequent, abstract = {Abstract: Frequent pattern mining is a heavily researched area in the field of data mining with wide range of applications. One of them is to use frequent pattern discovery methods in Web log data. Discovering hidden information from Web log data is called Web usage mining. The aim of discovering frequent patterns in Web log data is to obtain information about the navigational behavior of the users. This can be used for advertising purposes, for creating dynamic user profiles etc. In this paper three pattern mining approaches are investigated from the Web usage mining point of view. The different patterns in Web log mining are page sets, page sequences and page graphs.}, author = {Iváncsy, Renáta and Vajk, István}, interhash = {5612ed1c8203908fb94adf7ad8304e12}, intrahash = {f29f4627c9ae99370fc7ba005982e2e6}, journal = {Acta Polytechnica Hungarica}, number = 1, title = {Frequent Pattern Mining in Web Log Data}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.4559}, volume = 3, year = 2006 } @article{pasquier2005generating, author = {Pasquier, Nicolas and Taouil, Rafik and Bastide, Yves and Stumme, Gerd and Lakhal, Lotfi}, comment = {alpha}, interhash = {cb0ee99fae39f2a5e0af5be9d97978f5}, intrahash = {40f59a7fa7ce5015f9ee81709db89de0}, journal = {Journal Intelligent Information Systems (JIIS)}, number = 1, pages = {29-60}, publisher = {Kluwer Academic Publishers}, title = {Generating a Condensed Representation for Association Rules}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2005/pasquier2005generating.pdf}, volume = 24, year = 2005 } @inproceedings{kdml26, abstract = {We study the problem of listing all closed sets of a closure operator $\sigma$ that is a partial function on the power set of some finite ground set $E$, i.e., $\sigma : {\cal F} \to {\cal F}$ with ${\cal F} \subseteq {\cal P}(E)$. A very simple divide-and-conquer algorithm is analyzed that correctly solves this problem if and only if the domain of the closure operator is a strongly accessible set system. Strong accessibility is a strict relaxation of greedoids as well as of independence systems. This algorithm turns out to have delay $O (|E| (T_{\cal F} +T_\sigma + |E|))$ and space $O(|E| + S_{\cal F} S_\sigma)$, where $T_{\cal F}$, $S_{\cal F}$, $T_\sigma$, and $S_\sigma$ are the time and space complexities of checking membership in $\cal F$ and computing $\sigma$, respectively. In contrast, we show that the problem becomes intractable for accessible set systems. We relate our results to the data mining problem of listing all support-closed patterns of a dataset and show that there is a corresponding closure operator for all datasets if and only if the set system satisfies a certain confluence property.}, address = {Kassel, Germany}, author = {Boley, Mario and Horvath, Tamas and Poigne, Axel and Wrobel., Stefan}, booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen {\&} Adaptivitaet}, crossref = {lwa2010}, editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, interhash = {49ca7e8ee8dcb2236232e9653cb576d1}, intrahash = {75f0dabe405564eb640a8261edfce283}, presentation_end = {2010-10-06 10:45:00}, presentation_start = {2010-10-06 10:22:30}, room = {0446}, session = {kdml4}, title = {Listing closed sets of strongly accessible set systems with applications to data}, track = {kdml}, url = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml26.pdf}, year = 2010 } @article{pasquier2005generating, author = {Pasquier, Nicolas and Taouil, Rafik and Bastide, Yves and Stumme, Gerd and Lakhal, Lotfi}, comment = {alpha}, interhash = {cb0ee99fae39f2a5e0af5be9d97978f5}, intrahash = {40f59a7fa7ce5015f9ee81709db89de0}, journal = {Journal Intelligent Information Systems (JIIS)}, number = 1, pages = {29-60}, publisher = {Kluwer Academic Publishers}, title = {Generating a Condensed Representation for Association Rules}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2005/pasquier2005generating.pdf}, volume = 24, year = 2005 } @inproceedings{orlando02efficient, abstract = {Due to the huge increase in the number and dimension of available databases, efficient solutions for counting frequent sets are nowadays very important within the Data Mining community. Several sequential and parallel algorithms were proposed, whichin many cases exhibit excellent scalability. In this paper we present ParDCI, a distributed and multithreaded algorithm forcounting the occurrences of frequent sets within transactional databases. ParDCI is a parallel version of DCI (Direct Count& Intersect), a multi-strategy algorithm which is able to adapt its behavior not only to the features of the specific computingplatform (e.g. available memory), but also to the features of the dataset being processed (e.g. sparse or dense datasets).ParDCI enhances previous proposals by exploiting the highly optimized counting and intersection techniques of DCI, and byrelying on a multi-level parallelization approachwh ichex plicitly targets clusters of SMPs, an emerging computing platform.We focused our work on the efficient exploitation of the underlying architecture. Intra-Node multithreading effectively exploitsthe memory hierarchies of each SMP node, while Inter-Node parallelism exploits smart partitioning techniques aimed at reducingcommunication overheads. In depth experimental evaluations demonstrate that ParDCI reaches nearly optimal performances undera variety of conditions.}, author = {Orlando, Salvatore and Palmerini, Paolo and Perego, Raffaele and Silvestri, Fabrizio}, booktitle = {High Performance Computing for Computational Science — VECPAR 2002}, interhash = {50c17d100341c01892f7dd8fbd7deb69}, intrahash = {522c68b8bb5e28f1bf9f1e11e612f542}, pages = {3--29}, title = {An Efficient Parallel and Distributed Algorithm for Counting Frequent Sets}, url = {http://dx.doi.org/10.1007/3-540-36569-9_28}, year = 2003 } @article{tkde06, author = {Lucchese, Claudio and Orlando, Salvatore and Perego, Raffaele}, interhash = {33820f389bc1f6bdb96f5a8f925df879}, intrahash = {3aff1098bf9828a0c6683f07145d60bb}, journal = {IEEE Transactions On Knowledge and Data Engineering}, number = 1, pages = {21--36}, title = {Fast and Memory Efficient Mining of Frequent Closed Itemsets}, volume = 18, year = 2006 } @inproceedings{pasquier98pruning, author = {Pasquier, Nicolas and Bastide, Yves and Taouil, Rafik and Lakhal, Lotfi}, booktitle = {Bases de Donn�es Avanc�es}, crossref = {conf/bda/1998}, date = {2006-09-14}, editor = {Bouzeghoub, Mokrane}, interhash = {74868c54bf26d7cec48c0f8f219d5e67}, intrahash = {20dd28b712c5380c17f536734fb1a804}, title = {Pruning closed itemset lattices for associations rules.}, url = {http://dblp.uni-trier.de/db/conf/bda/bda98.html#PasquierBTL98}, year = 1998 } @inproceedings{pasquier98pruning, author = {Pasquier, Nicolas and Bastide, Yves and Taouil, Rafik and Lakhal, Lotfi}, booktitle = {Bases de Données Avancées}, crossref = {conf/bda/1998}, date = {2006-09-14}, editor = {Bouzeghoub, Mokrane}, interhash = {74868c54bf26d7cec48c0f8f219d5e67}, intrahash = {2fcd39ace346867762f3e6abe5a35ccb}, title = {Pruning closed itemset lattices for associations rules.}, url = {http://dblp.uni-trier.de/db/conf/bda/bda98.html#PasquierBTL98}, year = 1998 } @inproceedings{boulicaut00approximation, author = {Boulicaut, Jean-Francois and Bykowski, Artur and Rigotti, Christophe}, booktitle = {Principles of Data Mining and Knowledge Discovery}, interhash = {bcaa8a570d6b987b6171c4b7aff7cacd}, intrahash = {7e53b931a9ba3d36c7536f31901376bf}, pages = {75-85}, title = {Approximation of Frequency Queris by Means of Free-Sets}, url = {citeseer.ist.psu.edu/boulicaut00approximation.html}, year = 2000 }