@article{BirnickBlaesiusFriedrichetal.2020,
author = {Birnick, Johann and Bl{\"a}sius, Thomas and Friedrich, Tobias and Naumann, Felix and Papenbrock, Thorsten and Schirneck, Friedrich Martin},
title = {Hitting set enumeration with partial information for unique column combination discovery},
series = {Proceedings of the VLDB Endowment},
volume = {13},
journal = {Proceedings of the VLDB Endowment},
number = {11},
publisher = {Association for Computing Machinery},
address = {[New York, NY]},
issn = {2150-8097},
doi = {10.14778/3407790.3407824},
pages = {2270 -- 2283},
year = {2020},
abstract = {Unique column combinations (UCCs) are a fundamental concept in relational databases. They identify entities in the data and support various data management activities. Still, UCCs are usually not explicitly defined and need to be discovered. State-of-the-art data profiling algorithms are able to efficiently discover UCCs in moderately sized datasets, but they tend to fail on large and, in particular, on wide datasets due to run time and memory limitations.
In this paper, we introduce HPIValid, a novel UCC discovery algorithm that implements a faster and more resource-saving search strategy. HPIValid models the metadata discovery as a hitting set enumeration problem in hypergraphs. In this way, it combines efficient discovery techniques from data profiling research with the most recent theoretical insights into enumeration algorithms. Our evaluation shows that HPIValid is not only orders of magnitude faster than related work, it also has a much smaller memory footprint.},
language = {en}
}
@article{CaruccioDeufemiaNaumannetal.2021,
author = {Caruccio, Loredana and Deufemia, Vincenzo and Naumann, Felix and Polese, Giuseppe},
title = {Discovering relaxed functional dependencies based on multi-attribute dominance},
series = {IEEE transactions on knowledge and data engineering},
volume = {33},
journal = {IEEE transactions on knowledge and data engineering},
number = {9},
publisher = {Institute of Electrical and Electronics Engineers},
address = {New York, NY},
issn = {1041-4347},
doi = {10.1109/TKDE.2020.2967722},
pages = {3212 -- 3228},
year = {2021},
abstract = {With the advent of big data and data lakes, data are often integrated from multiple sources. Such integrated data are often of poor quality, due to inconsistencies, errors, and so forth. One way to check the quality of data is to infer functional dependencies (fds). However, in many modern applications it might be necessary to extract properties and relationships that are not captured through fds, due to the necessity to admit exceptions, or to consider similarity rather than equality of data values. Relaxed fds (rfds) have been introduced to meet these needs, but their discovery from data adds further complexity to an already complex problem, also due to the necessity of specifying similarity and validity thresholds. We propose Domino, a new discovery algorithm for rfds that exploits the concept of dominance in order to derive similarity thresholds of attribute values while inferring rfds. An experimental evaluation on real datasets demonstrates the discovery performance and the effectiveness of the proposed algorithm.},
language = {en}
}
@article{KossmannPapenbrockNaumann2021,
author = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix},
title = {Data dependencies for query optimization},
series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
volume = {31},
journal = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
number = {1},
publisher = {Springer},
address = {Berlin ; Heidelberg ; New York},
issn = {1066-8888},
doi = {10.1007/s00778-021-00676-3},
pages = {1 -- 22},
year = {2021},
abstract = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.},
language = {en}
}
@article{MomtaziNaumann2013,
author = {Momtazi, Saeedeh and Naumann, Felix},
title = {Topic modeling for expert finding using latent Dirichlet allocation},
series = {Wiley interdisciplinary reviews : Data mining and knowledge discovery},
volume = {3},
journal = {Wiley interdisciplinary reviews : Data mining and knowledge discovery},
number = {5},
publisher = {Wiley},
address = {San Fransisco},
issn = {1942-4787},
doi = {10.1002/widm.1102},
pages = {346 -- 353},
year = {2013},
abstract = {The task of expert finding is to rank the experts in the search space given a field of expertise as an input query. In this paper, we propose a topic modeling approach for this task. The proposed model uses latent Dirichlet allocation (LDA) to induce probabilistic topics. In the first step of our algorithm, the main topics of a document collection are extracted using LDA. The extracted topics present the connection between expert candidates and user queries. In the second step, the topics are used as a bridge to find the probability of selecting each candidate for a given query. The candidates are then ranked based on these probabilities. The experimental results on the Text REtrieval Conference (TREC) Enterprise track for 2005 and 2006 show that the proposed topic-based approach outperforms the state-of-the-art profile- and document-based models, which use information retrieval methods to rank experts. Moreover, we present the superiority of the proposed topic-based approach to the improved document-based expert finding systems, which consider additional information such as local context, candidate prior, and query expansion.},
language = {en}
}
@book{AlbrechtNaumann2012,
author = {Albrecht, Alexander and Naumann, Felix},
title = {Understanding cryptic schemata in large extract-transform-load systems},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-201-8},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257},
publisher = {Universit{\"a}t Potsdam},
pages = {19},
year = {2012},
abstract = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.},
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{HerschelNaumann2008,
author = {Herschel, Melanie and Naumann, Felix},
title = {Space and time scalability of duplicate detection in graph data},
isbn = {978-3-940793-46-1},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32851},
publisher = {Universit{\"a}t Potsdam},
year = {2008},
abstract = {Duplicate detection consists in determining different representations of real-world objects in a database. Recent research has considered the use of relationships among object representations to improve duplicate detection. In the general case where relationships form a graph, research has mainly focused on duplicate detection quality/effectiveness. Scalability has been neglected so far, even though it is crucial for large real-world duplicate detection tasks. In this paper we scale up duplicate detection in graph data (DDG) to large amounts of data and pairwise comparisons, using the support of a relational database system. To this end, we first generalize the process of DDG. We then present how to scale algorithms for DDG in space (amount of data processed with limited main memory) and in time. Finally, we explore how complex similarity computation can be performed efficiently. Experiments on data an order of magnitude larger than data considered so far in DDG clearly show that our methods scale to large amounts of data not residing in main memory.},
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}
}
@article{BonifatiMiorNaumannetal.2022,
author = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina},
title = {How inclusive are we?},
series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
volume = {50},
journal = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
number = {4},
publisher = {Association for Computing Machinery},
address = {New York},
issn = {0163-5808},
doi = {10.1145/3516431.3516438},
pages = {30 -- 35},
year = {2022},
abstract = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors.
We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.},
language = {en}
}
@article{VitaglianoJiangNaumann2021,
author = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix},
title = {Detecting layout templates in complex multiregion files},
series = {Proceedings of the VLDB Endowment},
volume = {15},
journal = {Proceedings of the VLDB Endowment},
number = {3},
publisher = {Association for Computing Machinery},
address = {New York},
issn = {2150-8097},
doi = {10.14778/3494124.3494145},
pages = {646 -- 658},
year = {2021},
abstract = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.},
language = {en}
}
@book{MeinelPlattnerDoellneretal.2014,
author = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick},
title = {Proceedings of the 7th Ph.D. Retreat of the HPI Research School on Service-oriented Systems Engineering},
publisher = {Universit{\"a}tsverlag Potsdam},
address = {Potsdam},
isbn = {978-3-86956-273-5},
url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63490},
publisher = {Universit{\"a}t Potsdam},
pages = {ii, 218},
year = {2014},
abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the Research Scholl, this technical report covers a wide range of research topics. These include but are not limited to: Self-Adaptive Service-Oriented Systems, Operating System Support for Service-Oriented Systems, Architecture and Modeling of Service-Oriented Systems, Adaptive Process Management, Services Composition and Workflow Planning, Security Engineering of Service-Based IT Systems, Quantitative Analysis and Optimization of Service-Oriented Systems, Service-Oriented Systems in 3D Computer Graphics sowie Service-Oriented Geoinformatics.},
language = {en}
}
@article{LosterKoumarelasNaumann2021,
author = {Loster, Michael and Koumarelas, Ioannis and Naumann, Felix},
title = {Knowledge transfer for entity resolution with siamese neural networks},
series = {ACM journal of data and information quality},
volume = {13},
journal = {ACM journal of data and information quality},
number = {1},
publisher = {Association for Computing Machinery},
address = {New York},
issn = {1936-1955},
doi = {10.1145/3410157},
pages = {25},
year = {2021},
abstract = {The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity-duplicates-into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise.
We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.},
language = {en}
}
@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}
}