With the increasing availability of large amounts of data in practically all application areas, the field of artificial intelligence (AI) has been attracting increasing attention for some time now. The new paradigm of data-driven AI, i.e. learning (domain) models and keeping them up-todate by using data mining techniques, is highly attractive because it reduces the effort of creating application systems. However, it also has many disadvantages. For example, models generated from data usually cannot be inspected and understood by a human being, and it is difficult to integrate already existing domain knowledge into learned models – prior or after learning.
The approaches to conceptual modelling as well as earlier approaches to AI have mainly been focusing on the manual engineering of models, which requires a great deal of time and money. Thus, depending on the application domain, these approaches scale up poorly. There is a huge potential in combining manual model engineering with data-driven model generation: the advantages of both approaches can be combined and their disadvantages be mitigated.
In this workshop, we are interested in all kinds of submissions at the intersection of the fields of conceptual modeling and AI. More specifically, we would like to see contributions that explore the value conceptual modeling brings to AI, and, vice versa, the value that AI can bring to conceptual modeling. Papers can be in one of the following categories:
1. Novel ideas and solutions
2. Critical reviews of problems and possible approaches
3. Agenda setting papers
Topics of Interest
Topics of interest include, but are not limited to:
- Combining learned and manually engineered models
- Combining symbolic with sub-symbolic models
- Conceptual (meta-)models as background knowledge for model learning
- Model validation
- Explainability of learned models
- Conceptual models for enabling explainability
- Trade-off between explainability and model performance
- Trade-off between comprehensibility of an explanation and its completeness
- Reasoning in learned models
- Data-driven modelling support
- Learning of meta-models
- Automatic, incremental model adaptation
Workshop Program (CEST)
*MoKI Session I **
09.00 - 09.15 Artifical Intelligence and Modeling – Setting the Scene
*Peter Fettke
09.15 - 10.00 Features of AI Solutions and their Use in AI Context Modeling
Jack Rittelmeyer and Kurt Sandkuhl
10.00 - 10.45 Modeling an Agricultural Process Coordination Problem to Enhance Efficiency and Resilience with Methods of Artificial Intelligence
Marvin Hubl
*MoKI Session II **
11.15 - 12.30 Moderated Discusstion about MoKI
*Ulrich Reimer (Moderator)
Important Dates
- Paper submission: extended until 05.05.2022
- Author notification: extended to 17.05.2022
- Camera-ready Version: 26.05.2022
Paper Submission and Format
We accept submission with a length between eight (8) and fourteen (14) pages plus additional up to four (4) pages for references. All papers need to be submitted via EasyChair and follow the GI Lecture Notes in Informatics formatting guidelines. In order to enable a uniform appearance of the contributions, we ask you to use the provided LaTeX format template. The LaTeX files must be submitted with the final version of the contribution. The MoKI workshop accepts papers in English and German language.
Publication
Accepted papers will be published as a joint collection with all workshop papers in the Digital Library of the Gesellschaft für Informatik (GI e.V.).
Workshop Organizers
- Dominik Bork, TU Wien, Austria
- Peter Fettke, German Research Center for Artificial Intelligence, Saarland University, Germany
- Ulrich Reimer, Eastern Switzerland University of Applied Sciences, Switzerland
Program Committee (TBC)
- Klaus-Dieter Althoff, German Research Center for AI, Germany
- Kerstin Bach, Norwegian University of Science and Technology, Norway
- Tatiana Endrjukaite, Transport and Telecommunication Institute, Latvia
- Michael Fellmann, University of Rostock, Germany
- Shirley Gregor, Australian National University, Canberra, Australia
- Knut Hinkelmann, University of Applied Sciences Northwestern Switzerland
- Manfred Jeusfeld, University of Skövde, Sweden
- Kamal Karlapalem, IIIT Hyderabad, India
- Roman Lukyanenko, HEC Montréal, Canada
- Wolfgang Maass, Saarland University, Germany
- Mirjam Minor, University of Frankfurt, Germany
- Jeffrey Parsons, Memorial University, St. John’s, Canada
- Thomas Roth-Berghofer, University of West London, UK
- Kurt Sandkuhl, University of Rostock, Germany
- Bernhard Thalheim, University of Kiel, Germany
- Isabelle Wattiau, ESSEC Business School, Paris, France
- Tatjana Welzer-Druzovec, Maribor University, Slovenia
- Rosina Weber, Drexel University, USA
- Mathias Weske, Universität Potsdam, HPI, Germany
- Stefan Wrobel, Fraunhofer IAIS, Germany