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.

@article{ivncsy2006frequent, author = {Iváncsy, Renáta and Vajk, István}, title = {Frequent Pattern Mining in Web Log Data}, journal = {Acta Polytechnica Hungarica}, year = {2006}, volume = {3}, number = {1}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.4559}, keywords = {association, frequent, itemset, mining, pattern, rule, weblog}, 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.} }

%0 = article %A = Iváncsy, Renáta and Vajk, István %D = 2006 %T = Frequent Pattern Mining in Web Log Data %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.4559

@article{tkde06, author = {Lucchese, Claudio and Orlando, Salvatore and Perego, Raffaele}, title = {Fast and Memory Efficient Mining of Frequent Closed Itemsets}, journal = {IEEE Transactions On Knowledge and Data Engineering}, year = {2006}, volume = {18}, number = {1}, pages = {21--36}, keywords = {association, closed, fca, frequent, itemset, mining, rule} }

%0 = article %A = Lucchese, Claudio and Orlando, Salvatore and Perego, Raffaele %D = 2006 %T = Fast and Memory Efficient Mining of Frequent Closed Itemsets

Due to the huge increase in the number and dimension of available databases, efficient solutions for counting frequent sets
e 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.

@inproceedings{orlando02efficient, author = {Orlando, Salvatore and Palmerini, Paolo and Perego, Raffaele and Silvestri, Fabrizio}, title = {An Efficient Parallel and Distributed Algorithm for Counting Frequent Sets}, booktitle = {High Performance Computing for Computational Science — VECPAR 2002}, year = {2003}, pages = {3--29}, url = {http://dx.doi.org/10.1007/3-540-36569-9_28}, keywords = {algorithm, fca, frequent, itemset, mining, parallel, set}, abstract = {Due to the huge increase in the number and dimension of available databases, efficient solutions for counting frequent sets
e 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.} }

%0 = inproceedings %A = Orlando, Salvatore and Palmerini, Paolo and Perego, Raffaele and Silvestri, Fabrizio %B = High Performance Computing for Computational Science — VECPAR 2002 %D = 2003 %T = An Efficient Parallel and Distributed Algorithm for Counting Frequent Sets %U = http://dx.doi.org/10.1007/3-540-36569-9_28

@inproceedings{bastide00levelwise, author = {Bastide, Y. and Taouil, R. and Pasquier, N. and Stumme, G. and Lakhal, L.}, title = {Levelwise Search of Frequent Patterns}, booktitle = {Actes des 16ièmes Journées Bases de Données Avancées}, publisher = {Blois}, address = {France}, year = {2000}, pages = {307-322}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2000/BDA00.pdf}, keywords = {2000, algorithm, algorithms, analysis, association, closed, concept, condensed, data, discovery, fca, formal, frequent, itemsets, kdd, knowledge, mining, myown, representations, rules} }

%0 = inproceedings %A = Bastide, Y. and Taouil, R. and Pasquier, N. and Stumme, G. and Lakhal, L. %B = Actes des 16ièmes Journées Bases de Données Avancées %C = France %D = 2000 %I = Blois %T = Levelwise Search of Frequent Patterns %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2000/BDA00.pdf

@article{bastide00miningfrequent, author = {Bastide, Y. and Taouil, R. and Pasquier, N. and Stumme, G. and Lakhal, L.}, title = {Mining Frequent Patterns with Counting Inference.}, journal = {SIGKDD Explorations, Special Issue on Scalable Algorithms}, year = {2000}, volume = {2}, number = {2}, pages = {71-80}, keywords = {2000, FCA, OntologyHandbook, analys, association, closed, concept, condensed, data, discovery, fca, formal, frequent, itemsets, kdd, knowledge, mining, myown, representation, representations, rule, rules} }

%0 = article %A = Bastide, Y. and Taouil, R. and Pasquier, N. and Stumme, G. and Lakhal, L. %D = 2000 %T = Mining Frequent Patterns with Counting Inference.

@inproceedings{bastide00miningminimal, author = {Bastide, Y. and Pasquier, N. and Taouil, R. and Stumme, G. and Lakhal, L.}, title = {Mining Minimal Non-Redundant Association Rules Using Frequent Closed Itemsets}, editor = {Lloyd, J. and Dahl, V. and Furbach, U. and Kerber, M. and Laus, K.-K. and Palamidessi, C. and Pereira, L.M. and Sagiv, Y. and Stuckey, P.J.}, booktitle = {Computational Logic --- CL 2000 Proc. CL'00}, series = {LNAI}, publisher = {Springer}, address = {Heidelberg}, year = {2000}, volume = {1861}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2000/DOOD00.pdf}, keywords = {2000, analys, association, closed, concept, condensed, data, discovery, fca, formal, frequent, itemsets, kdd, knowledge, mining, myown, representation, representations, rule, rules} }

%0 = inproceedings %A = Bastide, Y. and Pasquier, N. and Taouil, R. and Stumme, G. and Lakhal, L. %B = Computational Logic --- CL 2000 Proc. CL'00 %C = Heidelberg %D = 2000 %I = Springer %T = Mining Minimal Non-Redundant Association Rules Using Frequent Closed Itemsets %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2000/DOOD00.pdf

@article{DT99, author = {Dehaspe, L. and Toivonen, H.}, title = {Discovery of Frequent Datalog Patterns}, journal = {Data Mining and Knowledge Discovery}, year = {1999}, volume = {3}, number = {1}, pages = {7--36}, keywords = {frequent, discovery, datalog, pattern} }

%0 = article %A = Dehaspe, L. and Toivonen, H. %D = 1999 %T = Discovery of Frequent Datalog Patterns

@techreport{stumme99conceptualknowledge, author = {Stumme, G.}, title = {Conceptual Knowledge Discovery with Frequent Concept Lattices}, type = {FB4-Preprint 2043}, year = {1999}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/1999/P2043.pdf}, keywords = {1999, analysis, association, closed, concept, condensed, data, discovery, fca, formal, frequent, iceberg, itemsets, kdd, knowledge, lattices, mining, myown, representations, rule, rules} }

%0 = techreport %A = Stumme, G. %D = 1999 %T = Conceptual Knowledge Discovery with Frequent Concept Lattices %U = http://www.kde.cs.uni-kassel.de/stumme/papers/1999/P2043.pdf