@misc{KruseKaoudiQuianeRuizetal.2019,
  author    = {Kruse, Sebastian and Kaoudi, Zoi and Quiane-Ruiz, Jorge-Arnulfo and Chawla, Sanjay and Naumann, Felix and Contreras-Rojas, Bertty},
  title     = {Optimizing Cross-Platform Data Movement},
  series = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  journal   = {2019 IEEE 35th International Conference on Data Engineering (ICDE)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-7474-1},
  issn      = {1084-4627},
  doi       = {10.1109/ICDE.2019.00162},
  pages     = {1642 -- 1645},
  year      = {2019},
  abstract  = {Data analytics are moving beyond the limits of a single data processing platform. A cross-platform query optimizer is necessary to enable applications to run their tasks over multiple platforms efficiently and in a platform-agnostic manner. For the optimizer to be effective, it must consider data movement costs across different data processing platforms. In this paper, we present the graph-based data movement strategy used by RHEEM, our open-source cross-platform system. In particular, we (i) model the data movement problem as a new graph problem, which we prove to be NP-hard, and (ii) propose a novel graph exploration algorithm, which allows RHEEM to discover multiple hidden opportunities for cross-platform data processing.},
  language  = {en}
}
@article{DraisbachChristenNaumann2019,
  author    = {Draisbach, Uwe and Christen, Peter and Naumann, Felix},
  title     = {Transforming pairwise duplicates to entity clusters for high-quality duplicate detection},
  series = {ACM Journal of Data and Information Quality},
  volume    = {12},
  journal   = {ACM Journal of Data and Information Quality},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3352591},
  pages     = {1 -- 30},
  year      = {2019},
  abstract  = {Duplicate detection algorithms produce clusters of database records, each cluster representing a single real-world entity. As most of these algorithms use pairwise comparisons, the resulting (transitive) clusters can be inconsistent: Not all records within a cluster are sufficiently similar to be classified as duplicate. Thus, one of many subsequent clustering algorithms can further improve the result. <br /> We explain in detail, compare, and evaluate many of these algorithms and introduce three new clustering algorithms in the specific context of duplicate detection. Two of our three new algorithms use the structure of the input graph to create consistent clusters. Our third algorithm, and many other clustering algorithms, focus on the edge weights, instead. For evaluation, in contrast to related work, we experiment on true real-world datasets, and in addition examine in great detail various pair-selection strategies used in practice. While no overall winner emerges, we are able to identify best approaches for different situations. In scenarios with larger clusters, our proposed algorithm, Extended Maximum Clique Clustering (EMCC), and Markov Clustering show the best results. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.},
  language  = {en}
}