@article{JiangNaumann2020,
  author    = {Jiang, Lan and Naumann, Felix},
  title     = {Holistic primary key and foreign key detection},
  series = {Journal of intelligent information systems : JIIS},
  volume    = {54},
  journal   = {Journal of intelligent information systems : JIIS},
  number    = {3},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0925-9902},
  doi       = {10.1007/s10844-019-00562-z},
  pages     = {439 -- 461},
  year      = {2020},
  abstract  = {Primary keys (PKs) and foreign keys (FKs) are important elements of relational schemata in various applications, such as query optimization and data integration. However, in many cases, these constraints are unknown or not documented. Detecting them manually is time-consuming and even infeasible in large-scale datasets. We study the problem of discovering primary keys and foreign keys automatically and propose an algorithm to detect both, namely Holistic Primary Key and Foreign Key Detection (HoPF). PKs and FKs are subsets of the sets of unique column combinations (UCCs) and inclusion dependencies (INDs), respectively, for which efficient discovery algorithms are known. Using score functions, our approach is able to effectively extract the true PKs and FKs from the vast sets of valid UCCs and INDs. Several pruning rules are employed to speed up the procedure. We evaluate precision and recall on three benchmarks and two real-world datasets. The results show that our method is able to retrieve on average 88\% of all primary keys, and 91\% of all foreign keys. We compare the performance of HoPF with two baseline approaches that both assume the existence of primary keys.},
  language  = {en}
}
@misc{KruseKaoudiContrerasRojasetal.2020,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Contreras-Rojas, Bertty and Chawla, Sanjay and Naumann, Felix and Quian{\´e}-Ruiz, Jorge-Arnulfo},
  title     = {RHEEMix in the data jungle},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {6},
  doi       = {10.25932/publishup-51944},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-519443},
  pages     = {26},
  year      = {2020},
  abstract  = {Data analytics are moving beyond the limits of a single platform. In this paper, we present the cost-based optimizer of Rheem, an open-source cross-platform system that copes with these new requirements. The optimizer allocates the subtasks of data analytic tasks to the most suitable platforms. Our main contributions are: (i) a mechanism based on graph transformations to explore alternative execution strategies; (ii) a novel graph-based approach to determine efficient data movement plans among subtasks and platforms; and (iii) an efficient plan enumeration algorithm, based on a novel enumeration algebra. We extensively evaluate our optimizer under diverse real tasks. We show that our optimizer can perform tasks more than one order of magnitude faster when using multiple platforms than when using a single platform.},
  language  = {en}
}
@article{KruseKaoudiContrerasRojasetal.2020,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Contreras-Rojas, Bertty and Chawla, Sanjay and Naumann, Felix and Quiane-Ruiz, Jorge-Arnulfo},
  title     = {RHEEMix in the data jungle},
  series = {The VLDB Journal},
  volume    = {29},
  journal   = {The VLDB Journal},
  number    = {6},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-020-00612-x},
  pages     = {1287 -- 1310},
  year      = {2020},
  abstract  = {Data analytics are moving beyond the limits of a single platform. In this paper, we present the cost-based optimizer of Rheem, an open-source cross-platform system that copes with these new requirements. The optimizer allocates the subtasks of data analytic tasks to the most suitable platforms. Our main contributions are: (i) a mechanism based on graph transformations to explore alternative execution strategies; (ii) a novel graph-based approach to determine efficient data movement plans among subtasks and platforms; and (iii) an efficient plan enumeration algorithm, based on a novel enumeration algebra. We extensively evaluate our optimizer under diverse real tasks. We show that our optimizer can perform tasks more than one order of magnitude faster when using multiple platforms than when using a single platform.},
  language  = {en}
}