@phdthesis{Shaabani2020,
  author    = {Shaabani, Nuhad},
  title     = {On discovering and incrementally updating inclusion dependencies},
  doi       = {10.25932/publishup-47186},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-471862},
  school      = {Universit{\"a}t Potsdam},
  pages     = {119},
  year      = {2020},
  abstract  = {In today's world, many applications produce large amounts of data at an enormous rate. Analyzing such datasets for metadata is indispensable for effectively understanding, storing, querying, manipulating, and mining them. Metadata summarizes technical properties of a dataset which rang from basic statistics to complex structures describing data dependencies. One type of dependencies is inclusion dependency (IND), which expresses subset-relationships between attributes of datasets. Therefore, inclusion dependencies are important for many data management applications in terms of data integration, query optimization, schema redesign, or integrity checking. So, the discovery of inclusion dependencies in unknown or legacy datasets is at the core of any data profiling effort. For exhaustively detecting all INDs in large datasets, we developed S-indd++, a new algorithm that eliminates the shortcomings of existing IND-detection algorithms and significantly outperforms them. S-indd++ is based on a novel concept for the attribute clustering for efficiently deriving INDs. Inferring INDs from our attribute clustering eliminates all redundant operations caused by other algorithms. S-indd++ is also based on a novel partitioning strategy that enables discording a large number of candidates in early phases of the discovering process. Moreover, S-indd++ does not require to fit a partition into the main memory--this is a highly appreciable property in the face of ever-growing datasets. S-indd++ reduces up to 50\% of the runtime of the state-of-the-art approach. None of the approach for discovering INDs is appropriate for the application on dynamic datasets; they can not update the INDs after an update of the dataset without reprocessing it entirely. To this end, we developed the first approach for incrementally updating INDs in frequently changing datasets. We achieved that by reducing the problem of incrementally updating INDs to the incrementally updating the attribute clustering from which all INDs are efficiently derivable. We realized the update of the clusters by designing new operations to be applied to the clusters after every data update. The incremental update of INDs reduces the time of the complete rediscovery by up to 99.999\%. All existing algorithms for discovering n-ary INDs are based on the principle of candidate generation--they generate candidates and test their validity in the given data instance. The major disadvantage of this technique is the exponentially growing number of database accesses in terms of SQL queries required for validation. We devised Mind2, the first approach for discovering n-ary INDs without candidate generation. Mind2 is based on a new mathematical framework developed in this thesis for computing the maximum INDs from which all other n-ary INDs are derivable. The experiments showed that Mind2 is significantly more scalable and effective than hypergraph-based algorithms.},
  language  = {en}
}
@book{RanaMohapatraSidorovaetal.2022,
  author    = {Rana, Kaushik and Mohapatra, Durga Prasad and Sidorova, Julia and Lundberg, Lars and Sk{\"o}ld, Lars and Lopes Grim, Lu{\´i}s Fernando and Sampaio Gradvohl, Andr{\´e} Leon and Cremerius, Jonas and Siegert, Simon and Weltzien, Anton von and Baldi, Annika and Klessascheck, Finn and Kalancha, Svitlana and Lichtenstein, Tom and Shaabani, Nuhad and Meinel, Christoph and Friedrich, Tobias and Lenzner, Pascal and Schumann, David and Wiese, Ingmar and Sarna, Nicole and Wiese, Lena and Tashkandi, Araek Sami and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Schmidt, Christopher and H{\"u}gle, Johannes and Horschig, Siegfried and Uflacker, Matthias and Najafi, Pejman and Sapegin, Andrey and Cheng, Feng and Stojanovic, Dragan and Stojnev Ilić, Aleksandra and Djordjevic, Igor and Stojanovic, Natalija and Predic, Bratislav and Gonz{\´a}lez-Jim{\´e}nez, Mario and de Lara, Juan and Mischkewitz, Sven and Kainz, Bernhard and van Hoorn, Andr{\´e} and Ferme, Vincenzo and Schulz, Henning and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Fabian, Benjamin and Ermakova, Tatiana and Kelkel, Stefan and Baumann, Annika and Morgenstern, Laura and Plauth, Max and Eberhard, Felix and Wolff, Felix and Polze, Andreas and Cech, Tim and Danz, Noel and Noack, Nele Sina and Pirl, Lukas and Beilharz, Jossekin Jakob and De Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and Juiz, Carlos and Bermejo, Belen and M{\"u}hle, Alexander and Gr{\"u}ner, Andreas and Saxena, Vageesh and Gayvoronskaya, Tatiana and Weyand, Christopher and Krause, Mirko and Frank, Markus and Bischoff, Sebastian and Behrens, Freya and R{\"u}ckin, Julius and Ziegler, Adrian and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Sz{\´a}rnyas, G{\´a}bor and Marton, J{\´o}zsef and Maginecz, J{\´a}nos and Varr{\´o}, D{\´a}niel and Antal, J{\´a}nos Benjamin},
  title     = {HPI Future SOC Lab - Proceedings 2018},
  number    = {151},
  editor    = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-547-7},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56371},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-563712},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {x, 277},
  year      = {2022},
  abstract  = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2018. Selected projects have presented their results on April 17th and November 14th 2017 at the Future SOC Lab Day events.},
  language  = {en}
}