@inproceedings{orlando02efficient, title = {An Efficient Parallel and Distributed Algorithm for Counting Frequent Sets}, author = {Salvatore Orlando and Paolo Palmerini and Raffaele Perego and Fabrizio Silvestri}, booktitle = {High Performance Computing for Computational Science — VECPAR 2002}, pages = {3--29}, year = 2003, url = {http://dx.doi.org/10.1007/3-540-36569-9_28}, description = {SpringerLink - Book Chapter}, 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.}, biburl = {http://www.bibsonomy.org/bibtex/2522c68b8bb5e28f1bf9f1e11e612f542/jaeschke}, keywords = {parallel mining itemset set frequent fca algorithm} } @article{tkde06, title = {Fast and Memory Efficient Mining of Frequent Closed Itemsets}, author = {Claudio Lucchese and Salvatore Orlando and Raffaele Perego}, journal = {IEEE Transactions On Knowledge and Data Engineering}, number = 1, pages = {21--36}, volume = 18, year = 2006, biburl = {http://www.bibsonomy.org/bibtex/23aff1098bf9828a0c6683f07145d60bb/jaeschke}, keywords = {mining itemset association rule closed frequent fca} } @article{wu2008wu, title = {Top 10 algorithms in data mining}, address = {London}, author = {Xindong Wu and Vipin Kumar and J. Ross Quinlan and Joydeep Ghosh and Qiang Yang and Hiroshi Motoda and Geoffrey McLachlan and Angus Ng and Bing Liu and Philip Yu and Zhi-Hua Zhou and Michael Steinbach and David Hand and Dan Steinberg}, journal = {Knowledge and Information Systems}, month = {Jan}, number = 1, pages = {1--37}, publisher = {Springer}, volume = 14, year = 2008, url = {http://dx.doi.org/10.1007/s10115-007-0114-2}, issn = {0219-1377}, abstract = {This paper presents the top 10 data mining algorithms identified by the IEEE International Conference on Data Mining (ICDM) in December 2006: C4.5, k-Means, SVM, Apriori, EM, PageRank, AdaBoost, kNN, Naive Bayes, and CART. These top 10 algorithms are among the most influential data mining algorithms in the research community.With each algorithm, we provide a description of the algorithm, discuss the impact of the algorithm, and review current andfurther research on the algorithm. These 10 algorithms cover classification, clustering, statistical learning, associationanalysis, and link mining, which are all among the most important topics in data mining research and development.}, biburl = {http://www.bibsonomy.org/bibtex/22c34bb4b49187a6d3e780e78d254ae1f/jaeschke}, keywords = {icdm mining ieee data top algorithm} } @inproceedings{1244292, title = {FCA-based approach for mining contextualized folksonomy}, address = {New York, NY, USA}, author = {Hak Lae Kim and Suk Hyung Hwang and Hong Gee Kim}, booktitle = {SAC '07: Proceedings of the 2007 ACM symposium on Applied computing}, pages = {1340--1345}, publisher = {ACM Press}, year = 2007, url = {http://portal.acm.org/citation.cfm?id=1244002.1244292&coll=GUIDE&dl=}, location = {Seoul, Korea}, isbn = {1-59593-480-4}, doi = {http://doi.acm.org/10.1145/1244002.1244292}, biburl = {http://www.bibsonomy.org/bibtex/24440c3ca148004f3759456eac34e84fa/jaeschke}, keywords = {mining formal concept tagging social folksonomy analysis network fca} } @inproceedings{schmitz2006mining, title = {Mining Association Rules in Folksonomies}, address = {Berlin, Heidelberg}, annote = {Proc. of the 10th IFCS Conf.}, author = {Christoph Schmitz and Andreas Hotho and Robert Jäschke and Gerd Stumme}, booktitle = {Data Science and Classification}, editor = {V. Batagelj and H.-H. Bock and A. Ferligoj and A. Žiberna}, pages = {261--270}, publisher = {Springer}, series = {Studies in Classification, Data Analysis, and Knowledge Organization}, year = 2006, isbn = {978-3-540-34415-5}, biburl = {http://www.bibsonomy.org/bibtex/27f502f47bd0e584190337e3e2d4eba9e/jaeschke}, keywords = {mining 2006 association rule myown folksonomy l3s iccs_example trias_example} } @incollection{berendt04usage, title = {Usage Mining for and on the Semantic Web}, address = {Boston}, author = {Bettina Berendt and Andreas Hotho and Gerd Stumme}, booktitle = {Data Mining Next Generation Challenges and Future Directions}, editor = {Hillol Kargupta and Anupam Joshi and Krishnamoorthy Sivakumar and Yelena Yesha}, pages = {461-481}, publisher = {AAAI Press}, year = 2004, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2004/berendt04usage.pdf}, isbn = {0-262-61203-8}, abstract = {Semantic Web Mining aims at combining the two fast-developing research areas Semantic Web and Web Mining. Web Mining aims at discovering insights about the meaning of Web resources and their usage. Given the primarily syntactical nature of data Web mining operates on, the discovery of meaning is impossible based on these data only. Therefore, formalizations of the semantics of Web resources and navigation behavior are increasingly being used. This fits exactly with the aims of the Semantic Web: the Semantic Web enriches the WWW by machine-processable information which supports the user in his tasks. In this paper, we discuss the interplay of the Semantic Web with Web Mining, with a specific focus on usage mining.}, biburl = {http://www.bibsonomy.org/bibtex/20ef00fe39718eae61dca4d251b14578d/jaeschke}, keywords = {mining usage semantic web iccs_example trias_example} } @inproceedings{stumme02usage, title = {Usage Mining for and on the Semantic Web}, address = {Baltimore}, author = {G. Stumme and B. Berendt and A. Hotho}, booktitle = {Proc. NSF Workshop on Next Generation Data Mining}, month = {November}, pages = {77-86}, year = 2002, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/NSF-NGDM02.pdf}, comment = {alpha}, description = {Preliminary version of http://www.bibsonomy.org/bibtex/0a3c7992f2f6d8ecf7adc04aa6c2d5a22/stumme}, biburl = {http://www.bibsonomy.org/bibtex/24a68d1443065dcd7980989e97cb0af69/jaeschke}, keywords = {mining usage semantic web iccs_example trias_example} } @inproceedings{berendt02towards, title = {Towards Semantic Web Mining}, address = {Heidelberg}, author = {B. Berendt and A. Hotho and G. Stumme}, booktitle = {The Semantic Web -- ISWC 2002}, editor = {I. Horrocks and J. Hendler}, pages = {264-278}, publisher = {Springer}, series = {LNCS}, year = 2002, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/ISWC02.pdf}, comment = {alpha}, biburl = {http://www.bibsonomy.org/bibtex/2fc1c88be5f8c2640ca6e9a40b5fa1c7b/jaeschke}, keywords = {mining semantic web iccs_example trias_example} } @inproceedings{hartmann02semanticweb, title = {Semantic Web Mining for Building Information Portals (Position Paper)}, address = {Oldenburg}, author = {J. Hartmann and A. Hotho and G. Stumme}, booktitle = {Proc. Arbeitskreistreffen Knowledge Discovery}, month = {September}, year = 2002, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2002/hartmann2002semanticweb.pdf}, comment = {alpha}, biburl = {http://www.bibsonomy.org/bibtex/2a5f1a8b42409b96271bc5c671deceea9/jaeschke}, keywords = {mining semantic web iccs_example trias_example} } @inproceedings{berendt05semantic, title = {Semantic Web Mining and the Representation, Analysis, and Evolution of Web Space}, author = {Bettina Berendt and Andreas Hotho and Gerd Stumme}, booktitle = {Proc. of the 1st Intl. Workshop on Representation and Analysis of Web Space}, editor = {Vojtech Svatek and Vaclav Snasel}, pages = {1--16}, publisher = {Technical University of Ostrava}, year = 2005, isbn = {80-248-0864-1}, vgwort = {29}, biburl = {http://www.bibsonomy.org/bibtex/2f8826ba2790eeb857dd4becb31a08225/jaeschke}, keywords = {mining semantic web iccs_example trias_example} } @proceedings{stumme01semantic, title = {Semantic Web Mining}, address = {Freiburg}, editor = {G. Stumme and A. Hotho and B. Berendt}, month = {September 3rd,}, year = 2001, url = {http://semwebmine2001.aifb.uni-karlsruhe.de/online.html}, comment = {alpha}, description = {Proc. of the Semantic Web Mining Workshop of the 12th Europ. Conf. on Machine Learning (ECML'01) / 5th Europ. Conf. on Principles and Practice of Knowledge Discovery in Databases (PKDD'01)}, biburl = {http://www.bibsonomy.org/bibtex/2f6d06d221aab066b6cae38b595d35ffc/jaeschke}, keywords = {proceeding mining workshop semantic web iccs_example trias_example} } @proceedings{berendt05european, title = {Proc. of the European Web Mining Forum 2005}, editor = {Bettina Berendt and Andreas Hotho and Dunja Mladenic and Giovanni Semerano and Myra Spiliopoulou and Gerd Stumme and Maarten van Someren}, year = 2005, url = {http://www.kde.cs.uni-kassel.de/ws/ewmf05}, biburl = {http://www.bibsonomy.org/bibtex/2f306e43da22adede0286917d5d83eb3b/jaeschke}, keywords = {proceeding mining europe 2005 web iccs_example trias_example} } @inproceedings{studer03building, title = {Building and Using the Semantic Web}, address = {Osaka, Japan}, author = {Rudi Studer and Gerd Stumme and Siegfried Handschuh and Andreas Hotho and B. Motik}, booktitle = {New Trends in Knowledge Processing -- Data Mining, Semantic Web and Computational}, month = {March 10-11,}, pages = {31-34}, year = 2003, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2003/Sanken03.pdf}, comment = {alpha}, biburl = {http://www.bibsonomy.org/bibtex/2a0e7b52680f1876cdd9cd21f7cb2f95c/jaeschke}, keywords = {mining semantic web ontology iccs_example trias_example} } @inproceedings{hotho2006information, title = {Information Retrieval in Folksonomies: Search and Ranking}, address = {Heidelberg}, author = {Andreas Hotho and Robert Jäschke and Christoph Schmitz and Gerd Stumme}, booktitle = {The Semantic Web: Research and Applications}, editor = {York Sure and John Domingue}, month = {June}, pages = {411-426}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, volume = 4011, year = 2006, abstract = {Social bookmark tools are rapidly emerging on the Web. In such systems users are setting up lightweight conceptual structures called folksonomies. The reason for their immediate success is the fact that no specific skills are needed for participating. At the moment, however, the information retrieval support is limited. We present a formal model and a new search algorithm for folksonomies, called FolkRank, that exploits the structure of the folksonomy. The proposed algorithm is also applied to find communities within the folksonomy and is used to structure search results. All findings are demonstrated on a large scale dataset.}, biburl = {http://www.bibsonomy.org/bibtex/23c301945817681d637ee43901c016939/jaeschke}, keywords = {information mining 2006 pagerank seminar2006 myown retrieval l3s trias_example rank graph search folksonomy folkrank iccs_example ranking} } @inproceedings{1014146, title = {Mining scale-free networks using geodesic clustering}, address = {New York, NY, USA}, author = {Andrew Y. Wu and Michael Garland and Jiawei Han}, booktitle = {KDD '04: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining}, pages = {719--724}, publisher = {ACM Press}, year = 2004, url = {http://doi.acm.org/10.1145/1014052.1014146}, isbn = {1-58113-888-1}, abstract = { Many real-world graphs have been shown to be scale-free---vertex degrees follow power law distributions, vertices tend to cluster, and the average length of all shortest paths is small. We present a new model for understanding scale-free networks based on multilevel geodesic approximation, using a new data structure called a multilevel mesh.Using this multilevel framework, we propose a new kind of graph clustering for data reduction of very large graph systems such as social, biological, or electronic networks. Finally, we apply our algorithms to real-world social networks and protein interaction graphs to show that they can reveal knowledge embedded in underlying graph structures. We also demonstrate how our data structures can be used to quickly answer approximate distance and shortest path queries on scale-free networks. }, biburl = {http://www.bibsonomy.org/bibtex/2ace73eceff27aaba6e70b390c2f3000f/jaeschke}, keywords = {mining scale free network clustering} } @article{kb00web, title = {Web Mining Research: {A} Survey}, author = {R. Kosala and H. Blockeel}, journal = {SIGKDD Explorations}, number = 1, pages = {1-15}, publisher = {ACM}, volume = 2, year = 2000, url = {citeseer.nj.nec.com/kosala00web.html}, biburl = {http://www.bibsonomy.org/bibtex/259f6ef686827c7095cc89ebdb056a222/jaeschke}, keywords = {mining usage survey web} } @article{gd05link, title = {Link mining: a survey}, address = {New York, NY, USA}, author = {Lise Getoor and Christopher P. Diehl}, journal = {SIGKDD Explor. Newsl.}, number = 2, pages = {3--12}, publisher = {ACM Press}, volume = 7, year = 2005, url = {http://www.cpdiehl.org/lmsurvey.pdf}, doi = {http://doi.acm.org/10.1145/1117454.1117456}, biburl = {http://www.bibsonomy.org/bibtex/2ac02f1d7dea7a106bc4103c8a9ec4aef/jaeschke}, keywords = {mining graph seminar2006 link web} }