Publications AS: Bibliography 2025 BibTeX
@inproceedings {INPROC-2025-06,
author = {Julius Voggesberger and Peter Reimann and Dennis Treder-Tschechlov and Bernhard Mitschang},
title = {{Auto-CEn: AutoML for Classifier Ensembles - Diversity-Based Classifier Selection and Decision Fusion Optimization}},
booktitle = {2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)},
editor = {IEEE},
publisher = {IEEE},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
pages = {1--10},
type = {Conference Paper},
month = {October},
year = {2025},
isbn = {979-8-3315-1179-1},
language = {English},
cr-category = {I.2 Artificial Intelligence},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {Classifier ensembles are mainly used for classification problems exhibiting
complex data characteristics, e.g., a high class imbalance. They consist of a
set of classifiers and a decision fusion method that combines the predictions
of the classifiers. However, creating an accurate ensemble is a challenging
optimization problem, since the individual classifiers and the decision fusion
method must be selected from a huge search space that consists of numerous
classification and fusion algorithms. Thereby, the selected classifiers have to
be both accurate and diverse, so that they complement each other and make
correct predictions on different data subsets. In addition, the selected
decision fusion method has to accurately combine the predictions of individual
classifiers into a consensus decision. Current literature focuses on AutoML
approaches that reduce the complexity of the optimization problem by omitting
the optimization of the classifier diversity and of the decision fusion. In
this paper, we propose Auto-CEn as a novel ensemble approach based on AutoML
that efficiently solves the optimization problem by selecting a set of accurate
and diverse classifiers for the ensemble and by optimizing the decision fusion.
In our extensive evaluation on 20 real-world datasets, we show that Auto-CEn
outperforms several state-of-the-art baselines and that this improvement is
mainly attributed to its novel contributions of diversity-based classifier
selection and decision fusion optimization.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-06&engl=1}
}
@inproceedings {INPROC-2025-05,
author = {Laura Schuiki and Corinna Giebler and Eva Hoos and Holger Schwarz},
title = {{Unraveling Data Mesh: Current State, Challenges and Research Gaps}},
booktitle = {Service-Oriented Computing: 19th Symposium and Summer School, SummerSOC 2025, Crete, Greece, June 16–21, 2025, Revised Selected Papers},
publisher = {Springer, Cham},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
series = {Communications in Computer and Information Science},
volume = {2602},
pages = {59--79},
type = {Conference Paper},
month = {October},
year = {2025},
isbn = {"DOI: https://doi.org/10.1007/978-3-032-07313-6"},
language = {English},
cr-category = {H.2.1 Database Management Logical Design,
H.2.4 Database Management Systems},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {Despite the emergence and rapid growth in popularity of data mesh in recent
years, it is still a relatively new concept and there is still a lot of
research to be done before it is fully explored. In particular it is unclear
how a complete data mesh can be successfully implemented. As a first step, it
is necessary to identify open implementation challenges in order to identify
research gaps that will point researchers in the right direction. In
particular, it is important to consider both literature and practical
applications as sources of knowledge. To this end, we conducted a literature
review and interviews with industry experts from a globally operating
industrial company. Thereby we focused on the technical challenges associated
with implementing a data mesh in a company with a well-established data
infrastructure. In addition, we derived research gaps from these challenges
that need to be addressed in future work.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-05&engl=1}
}
@inproceedings {INPROC-2025-04,
author = {Laura Schuiki and Ulf Schreier and Holger Schwarz and Bernhard Mitschang},
title = {{A Data Product Classification by Technical and Machine Learning Aspects}},
booktitle = {Database and Expert Systems Applications: 36th International Conference, DEXA 2025, Bangkok, Thailand, August 25–27, 2025, Proceedings, Part I},
publisher = {Springer Berlin Heidelberg},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
pages = {338--344},
type = {Conference Paper},
month = {September},
year = {2025},
isbn = {10.1007/978-3-032-02049-9_27},
language = {English},
cr-category = {H.2.1 Database Management Logical Design,
H.2.4 Database Management Systems},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {Similar to the software services methodology, data products (DP) can be seen as
a kind of data services that specify all important issues for data provisioning
and data consumption. DPs come in many different varieties stretching from
simple data pipelines to complex machine learning models and model inferences
and, above all, typically result in complex data networks. It is time to come
up with a useful categorization and structuring of the DP topic in order to
conquer complexity. In this paper, we present and assess a basic classification
approach that focuses on DP characteristics and thus provides the basis for
blueprinting and architectural discussions.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-04&engl=1}
}
@inproceedings {INPROC-2025-03,
author = {Andrea Fieschi and Pascal Hirmer and Christoph Stach},
title = {{Discovering Suitable Anonymization Techniques: A Privacy Toolbox for Data Experts}},
booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2025)},
editor = {Meike Klettke and Ralf Schenkel and Andreas Heinrich and Daniela Nicklas and Maximilian E. Sch{\"u}le and Klaus Meyer-Wegener},
address = {Bonn},
publisher = {Gesellschaft f{\"u}r Informatik},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
series = {Lecture Notes in Informatics},
volume = {P361},
pages = {827--833},
type = {Demonstration},
month = {March},
year = {2025},
issn = {2944-7682},
doi = {10.18420/BTW2025-48},
keywords = {Anonymization; Privacy-Enhancing Techniques; Anonymization by Design},
language = {English},
cr-category = {K.4.1 Computers and Society Public Policy Issues},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {Identifying the appropriate anonymization technique is a critical yet
challenging task for developers, data scientists, and security practitioners.
Our interactive toolbox addresses this challenge by providing a comprehensive
overview of available anonymization techniques to assist privacy-conscious
developers in selecting the right one for their specific use cases. The toolbox
offers a hierarchical and classified overview of techniques, each detailed with
meta-model information. It employs a modular approach, allowing techniques to
be implemented and deployed independently. Additionally, it enables developers
to evaluate these techniques on test datasets. Our toolbox allows for the easy
addition of new categories and modules. This paper demonstrates the
anonymization toolbox{\^a}€™s capabilities, simplifying the decision-making process
in the Anonymization by Design cycle by ensuring overview, modularity, and
flexibility.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-03&engl=1}
}
@inproceedings {INPROC-2025-02,
author = {Andrea Fieschi and Pascal Hirmer and Christoph Stach and Bernhard Mitschang},
title = {{Characterising and Categorising Anonymization Techniques: A Literature-Based Approach}},
booktitle = {Proceedings of the 11th International Conference on Information Systems Security and Privacy - Volume 1 (ICISSP 2025)},
editor = {Roberto Di Pietro and Karen Renaud and Paolo Mori},
publisher = {SciTePress},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
pages = {107--118},
type = {Conference Paper},
month = {February},
year = {2025},
isbn = {978-989-758-735-1},
issn = {2184-4356},
doi = {10.5220/0013379100003899},
keywords = {Privacy Protection; PRISMA Systematic Literature Research; Privacy-Enhancing Techniques; Anonymization Techniques},
language = {English},
cr-category = {K.4.1 Computers and Society Public Policy Issues},
contact = {Senden Sie eine E-Mail an \<andrea.fieschi@ipvs.uni-stuttgart.de\>.},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {Anonymization plays a crucial role in protecting personal data and ensuring
information security. However, selecting the appropriate anonymization
technique is a challenging task for developers, data scientists, and security
practitioners due to the vast array of techniques available in both research
and practice. This paper aims to assist users by offering a method for
structuring a framework that helps them make informed decisions about the most
appropriate anonymization techniques for their specific use cases. To achieve
this, we first conduct a systematic literature review following the PRISMA
guidelines to capture the current state of the art in anonymization techniques.
Based on the findings from this review, we propose a conceptual organisation of
anonymization techniques, designed to help users navigate the complex landscape
of anonymization and choose techniques that align with their security
requirements.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-02&engl=1}
}
@inproceedings {INPROC-2025-01,
author = {Laura Schuiki and Christoph Stach and Corinna Giebler and Eva Hoos and Bernhard Mitschang},
title = {{Enabling Trusted Data Sharing in Data Spaces: PROTON - A Privacy-by-Design Approach to Data Products}},
booktitle = {Proceedings of the 11th International Conference on Information Systems Security and Privacy - Volume 1 (ICISSP 2025)},
editor = {Roberto Di Pietro and Karen Renaud and Paolo Mori},
publisher = {SciTePress},
institution = {University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Germany},
pages = {95--106},
type = {Conference Paper},
month = {February},
year = {2025},
isbn = {978-989-758-735-1},
issn = {2184-4356},
doi = {10.5220/0013372900003899},
keywords = {Distributed Data Management; Data Product; Privacy},
language = {English},
cr-category = {E.1 Data Structures,
K.4.1 Computers and Society Public Policy Issues},
contact = {Senden Sie eine E-Mail an \<laura-sophie.schuiki@ipvs.uni-stuttgart.de\>.},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {In the current era of data-driven innovation, the value of data can be
significantly enhanced by facilitating its dissemination. In this context, the
data mesh concept has gained popularity in recent years. Data Mesh includes
domain experts who design so-called data products. It is imperative that all
parties involved have trust in these data products. This applies in particular
to data subjects who share their data, data owners who create the data
products, and data consumers who use them. To establish such trust, privacy
approaches are key. Due to the decentralized and distributed nature of data
mesh, however, traditional privacy strategies cannot be applied. To address
this issue, we present PROTON, a concept that facilitates the handling of
PRivacy-cOmpliant daTa prOducts by desigN. PROTON is based on three pillars: a
comprehensive description model for privacy requirements, an extended creation
process that adheres to these requirements when compiling data products, and a
refined access process for verifying compliance prior to data sharing. The
practical applicability of PROTON is illustrated by means of a real-world
application scenario that has been devised in collaboration with domain experts
from our industry partner.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2025-01&engl=1}
}
@article {ART-2025-01,
author = {Ulf Schreier and Peter Reimann and Bernhard Mitschang},
title = {{A Kanban-based Approach to Manage Machine Learning Projects in Manufacturing}},
journal = {Procedia CIRP: Proceedings of the 58th CIRP Conference on Manufacturing Systems (CIRP CMS)},
publisher = {Elsevier},
volume = {134},
pages = {109--114},
type = {Article in Journal},
month = {April},
year = {2025},
doi = {10.1016/j.procir.2025.03.011},
keywords = {Machine learning (ML); ML project management, machine learning operations (MLOps); Kanban; Scrum},
language = {English},
cr-category = {H.2.8 Database Applications},
department = {University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems},
abstract = {A growing number of machine learning (ML) projects in manufacturing require the
collaboration of various experts. In addition to data scientists, stakeholders
with production engineering knowledge have to specify and prioritize individual
project tasks. Data engineers prepare input data, while machine learning
operations (MLOps) engineers ensure that trained models are deployed and
monitored within IT landscapes. Existing project management approaches, e.g.,
Scrum, have problems for ML projects, as they do not consider various expert
roles or ML project stages. We propose a project management approach defining a
Kanban workflow by readjusting stages of ML development lifecycles, e.g., CRISP
DM. This makes it possible to map expert roles to stages of the Kanban
workflow. An adapted Kanban board allows visualizing and reviewing the status
of all project tasks. We validate our approach with specific use cases, showing
that it facilitates ML project management in manufacturing.},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=ART-2025-01&engl=1}
}
