@book{AbedjanNaumann2011,
  author    = {Abedjan, Ziawasch and Naumann, Felix},
  title     = {Advancing the discovery of unique column combinations},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-148-6},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53564},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {25},
  year      = {2011},
  abstract  = {Unique column combinations of a relational database table are sets of columns that contain only unique values. Discovering such combinations is a fundamental research problem and has many different data management and knowledge discovery applications. Existing discovery algorithms are either brute force or have a high memory load and can thus be applied only to small datasets or samples. In this paper, the wellknown GORDIAN algorithm and "Apriori-based" algorithms are compared and analyzed for further optimization. We greatly improve the Apriori algorithms through efficient candidate generation and statistics-based pruning methods. A hybrid solution HCAGORDIAN combines the advantages of GORDIAN and our new algorithm HCA, and it significantly outperforms all previous work in many situations.},
  language  = {en}
}
@book{BauckmannAbedjanLeseretal.2012,
  author    = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix},
  title     = {Covering or complete? : Discovering conditional inclusion dependencies},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-212-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {34},
  year      = {2012},
  abstract  = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.},
  language  = {en}
}
@book{AbedjanGolabNaumannetal.,
  author    = {Abedjan, Ziawasch and Golab, Lukasz and Naumann, Felix and Papenbrock, Thorsten},
  title     = {Data Profiling},
  series = {Synthesis lectures on data management, 52},
  journal   = {Synthesis lectures on data management, 52},
  publisher = {Morgan \& Claypool Publishers},
  address   = {San Rafael},
  isbn      = {978-1-68173-446-0},
  pages     = {xviii, 136},
  language  = {en}
}