@misc{ShaabaniMeinel2018,
  author    = {Shaabani, Nuhad and Meinel, Christoph},
  title     = {Improving the efficiency of inclusion dependency detection},
  series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  journal   = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-6014-2},
  doi       = {10.1145/3269206.3271724},
  pages     = {207 -- 216},
  year      = {2018},
  abstract  = {The detection of all inclusion dependencies (INDs) in an unknown dataset is at the core of any data profiling effort. Apart from the discovery of foreign key relationships, INDs can help perform data integration, integrity checking, schema (re-)design, and query optimization. With the advent of Big Data, the demand increases for efficient INDs discovery algorithms that can scale with the input data size. To this end, we propose S-INDD++ as a scalable system for detecting unary INDs in large datasets. S-INDD++ applies a new stepwise partitioning technique that helps discard a large number of attributes in early phases of the detection by processing the first partitions of smaller sizes. S-INDD++ also extends the concept of the attribute clustering to decide which attributes to be discarded based on the clustering result of each partition. Moreover, in contrast to the state-of-the-art, S-INDD++ does not require the partition to fit into the main memory-which is a highly appreciable property in the face of the ever growing datasets. We conducted an exhaustive evaluation of S-INDD++ by applying it to large datasets with thousands attributes and more than 266 million tuples. The results show the high superiority of S-INDD++ over the state-of-the-art. S-INDD++ reduced up to 50 \% of the runtime in comparison with BINDER, and up to 98 \% in comparison with S-INDD.},
  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}
}