@phdthesis{Papenbrock2017,
  author    = {Papenbrock, Thorsten},
  title     = {Data profiling - efficient discovery of dependencies},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406705},
  school      = {Universit{\"a}t Potsdam},
  pages     = {viii, ii, 141},
  year      = {2017},
  abstract  = {Data profiling is the computer science discipline of analyzing a given dataset for its metadata. The types of metadata range from basic statistics, such as tuple counts, column aggregations, and value distributions, to much more complex structures, in particular inclusion dependencies (INDs), unique column combinations (UCCs), and functional dependencies (FDs). If present, these statistics and structures serve to efficiently store, query, change, and understand the data. Most datasets, however, do not provide their metadata explicitly so that data scientists need to profile them. While basic statistics are relatively easy to calculate, more complex structures present difficult, mostly NP-complete discovery tasks; even with good domain knowledge, it is hardly possible to detect them manually. Therefore, various profiling algorithms have been developed to automate the discovery. None of them, however, can process datasets of typical real-world size, because their resource consumptions and/or execution times exceed effective limits. In this thesis, we propose novel profiling algorithms that automatically discover the three most popular types of complex metadata, namely INDs, UCCs, and FDs, which all describe different kinds of key dependencies. The task is to extract all valid occurrences from a given relational instance. The three algorithms build upon known techniques from related work and complement them with algorithmic paradigms, such as divide \& conquer, hybrid search, progressivity, memory sensitivity, parallelization, and additional pruning to greatly improve upon current limitations. Our experiments show that the proposed algorithms are orders of magnitude faster than related work. They are, in particular, now able to process datasets of real-world, i.e., multiple gigabytes size with reasonable memory and time consumption. Due to the importance of data profiling in practice, industry has built various profiling tools to support data scientists in their quest for metadata. These tools provide good support for basic statistics and they are also able to validate individual dependencies, but they lack real discovery features even though some fundamental discovery techniques are known for more than 15 years. To close this gap, we developed Metanome, an extensible profiling platform that incorporates not only our own algorithms but also many further algorithms from other researchers. With Metanome, we make our research accessible to all data scientists and IT-professionals that are tasked with data profiling. Besides the actual metadata discovery, the platform also offers support for the ranking and visualization of metadata result sets. Being able to discover the entire set of syntactically valid metadata naturally introduces the subsequent task of extracting only the semantically meaningful parts. This is challenge, because the complete metadata results are surprisingly large (sometimes larger than the datasets itself) and judging their use case dependent semantic relevance is difficult. To show that the completeness of these metadata sets is extremely valuable for their usage, we finally exemplify the efficient processing and effective assessment of functional dependencies for the use case of schema normalization.},
  language  = {en}
}
@phdthesis{Ostrowski2018,
  author    = {Ostrowski, Max},
  title     = {Modern constraint answer set solving},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-407799},
  school      = {Universit{\"a}t Potsdam},
  pages     = {135},
  year      = {2018},
  abstract  = {Answer Set Programming (ASP) is a declarative problem solving approach, combining a rich yet simple modeling language with high-performance solving capabilities. Although this has already resulted in various applications, certain aspects of such applications are more naturally modeled using variables over finite domains, for accounting for resources, fine timings, coordinates, or functions. Our goal is thus to extend ASP with constraints over integers while preserving its declarative nature. This allows for fast prototyping and elaboration tolerant problem descriptions of resource related applications. The resulting paradigm is called Constraint Answer Set Programming (CASP). We present three different approaches for solving CASP problems. The first one, a lazy, modular approach combines an ASP solver with an external system for handling constraints. This approach has the advantage that two state of the art technologies work hand in hand to solve the problem, each concentrating on its part of the problem. The drawback is that inter-constraint dependencies cannot be communicated back to the ASP solver, impeding its learning algorithm. The second approach translates all constraints to ASP. Using the appropriate encoding techniques, this results in a very fast, monolithic system. Unfortunately, due to the large, explicit representation of constraints and variables, translation techniques are restricted to small and mid-sized domains. The third approach merges the lazy and the translational approach, combining the strength of both while removing their weaknesses. To this end, we enhance the dedicated learning techniques of an ASP solver with the inferences of the translating approach in a lazy way. That is, the important knowledge is only made explicit when needed. By using state of the art techniques from neighboring fields, we provide ways to tackle real world, industrial size problems. By extending CASP to reactive solving, we open up new application areas such as online planning with continuous domains and durations.},
  language  = {en}
}