%Aigaion2 BibTeX export from Knowledge Engineering Publications
%Tuesday 19 January 2021 01:16:27 AM

@MISC{bh:deepDB2019,
        author = {Hilprecht, Benjamin and Schmidt, Andreas and Kulessa, Moritz and Molina, Alejandro and Kersting, Kristian and Binnig, Carsten},
      keywords = {Databases, Deep Learning, SQL Queries, Sum-Product Networks},
         month = sep,
         title = {DeepDB: Learn from Data, not from Queries!},
          year = {2019},
  howpublished = {arXiv preprint arXiv:1909.00607},
           url = {https://arxiv.org/pdf/1909.00607.pdf},
      abstract = {The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major downsides. First, collecting the training data can be very expensive, since all queries need to be executed on potentially large databases. Second, training data has to be recollected when the workload and the data changes. To overcome these limitations, we take a different route: we propose to learn a pure data-driven model that can be used for different tasks such as query answering or cardinality estimation. This data-driven model also supports ad-hoc queries and updates of the data without the need of full retraining when the workload or data changes. Indeed, one may now expect that this comes at a price of lower accuracy since workload-driven models can make use of more information. However, this is not the case. The results of our empirical evaluation demonstrate that our data-driven approach not only provides better accuracy than state-of-the-art learned components but also generalizes better to unseen queries.}
}