The Semantic Data Mining (SEDAMI) Workshop 2021

SEDAMI webapge is http://sedami.geist.re

The theme of the SEDAMI workshop is semantic data mining. With this workshop we aim to get an insight into the current status of research in this area. We focus mainly on methods that allow include/utilize/exploit semantic information and domain knowledge in the context of machine learning and data mining, focusing on domains and research questions that have not been deeply investigated so far and to improve solutions to classic tasks. We encourage contributions on methods, techniques and applications that are both domain-specific but also transversal to different application domains. In particular, we solicit contributions that aim to focus on semantic data mining for providing and/or enhancing interpretability, the introduction and preservation of knowledge, as well as the provisioning of explanations.

The 1st edition of SEDAMI was co-located with 30th International Joint Conference on Artificial Intelligence (IJCAI-21)

Organising committee

  • Martin Atzmueller, Osnabrück University, Germany,
  • Grzegorz J. Nalepa, Jagiellonian University, Poland
  • Szymon Bobek, Jagiellonian University
  • Nada Lavrac, Jožef Stefan Institute, Slovenia

SEDAMI 2021 at IJCAI 2021

Important dates

  • Submission Deadline: May 13, 2021 (AoE)
  • We plan to have a rolling review process for late/breaking papers of 5-6 pp. This will be kept open for up to 1 months after the regular deadlines
  • Notification of Acceptance: May 25, 2021 (AoE)
  • Camera-Ready Versions Due: June 6, 2021 (AoE)
  • Workshop date: August 21-26, 2021

Schedule

Aug 20 10:00 – 13:30 Montreal Time (UTC-4)

Please note, that all times are in UTC-4 (this is e.g., CEST-6 … 10:00 UTC-4 is 16:00 CEST)

10:00-10:15 SEDAMI 2021 - Opening (Chair: Martin Atzmueller)

10:15-11:45 Session 1 - Foundations (Chair: Szymon Bobek)
10:15-10:45 Victor Guimarães and Vítor Costa: Meta-Interpretive Learning meets Neural Networks
10:45-11:15 Blaž Škrlj and Nada Lavrač: Towards Explainable Relational Boosting via Propositionalization
11:15-11:45 Dietmar Seipel and Martin Atzmueller: Declarative Knowledge Discovery in Databases via Meta-Learning - Towards Advanced Analytics

11:45-12:00 Break

12:00-13:00 Session 2 - Modeling & Application (Chair: Nada Lavrac)
12:00-12:30 Shaobo Wang, Guangliang Liu, Wenyan Zhu, Zengtao Jiao, Haichen Lv, Jun Yan and Yunlong Xia: Interpretable Knowledge Mining for Heart Failure Prognosis Risk Evaluation
12:30-13:00 Dan Hudson, Leonid Schwenke, Stefan Bloemheuvel, Arnab Ghosh Chowdhury, Nils Schut and Martin Atzmueller: Knowledge-Augmented Induction of Complex Networks on Supply-Demand-Material Data

13:00-13:30 Closing (Chair: Grzegorz J. Nalepa)

Call for papers

Motivation for the workshop

The general goal of data mining is to uncover novel, interesting, and ultimately understandable patterns, cf. (Fayyad 1996), i.e., relating to valuable, useful and implicit knowledge. Looking at the development of data mining in the last decades, it can be observed that not only the data mining tasks used to be more restricted, but also the applied data mining workflows were simpler. Thus, recent advances of data mining and machine learning apparently bring new challenges in its practical use in data mining, including interpretability, introduction and preservation of knowledge, as well as the provisioning of explanations. Using semantic information such as domain/background knowledge in data mining is a promising emerging direction for addressing these problems, where the knowledge is typically represented in a knowledge repository, such as an ontology, or a knowledge base. The main aspect of semantic data mining, which we focus on in this workshop, is the explicit integration of this knowledge into the data mining and knowledge discovery modeling step, where the algorithms for data mining/modeling or post-processing make use of the formalized knowledge to improve the overall results.

Topics of interest

Overall, we are interested in receiving papers related to the following topics which include but are not limited to:

  • Declarative data mining
  • Declarative domain knowledge
  • Knowledge modelling and data mining
  • Data mining and machine learning using ontologies
  • Introduction of semantics into the data mining process
  • Interpretable models in data mining and machine learning
  • Knowledge-based data mining and machine learning approaches
  • Role of explanations in data mining and machine learning
  • Knowledge-graphs in data mining and machine learning
  • Feature engineering for transparency and explanation
  • Transparent and hybrid models in machine learning
  • Inductive logic programming and data mining
  • Human in the loop of the data mining process
  • Role of Linked Open Data in data mining
  • Applications of all of the above

Program Committee (tentative)

  • Klaus-Dieter Althoff, University of Hildesheim & DFKI, Germany
  • Martin Atzmueller, Osnabrück University, Germany
  • Przemysław Biecek, Warsaw University of Technology, Poland
  • Szymon Bobek, Jagiellonian University, Poland
  • João Gama, University of Porto, Portugal
  • Nada Lavrac, Jožef Stefan Institute, Slovenia
  • Stan Matwin, Dalhousie University, Canada
  • Grzegorz J. Nalepa, Jagiellonian University, Poland
  • Sławomir Nowaczyk, Halmstad University, Sweden
  • Jose Palma, Universidad de Murcia, Spain
  • Juan Pavon, Universidad Complutense de Madrid, Spain
  • Marc Plantevit, Université Lyon, France
  • Eric Postma, Tilburg University, The Netherlands
  • Céline Rouveirol, Université Sorbonne Paris Nord, France
  • Marek Sikora, Silesian University of Technology, Poland
  • Blaž Škrlj, Jožef Stefan Institute, Slovenia

Submission details

Please submit papers using the dedicated Easychair We are accepting short papers – 5-6 pages with references, and long papers – 10-12 pages. We are encouraging both original research papers, as well position papers. All submissions should be formatted using the Springer LNCS format. Workshop proceedings will be made available by CEUR-WS. A post workshop journal publication is considered.

Furthermore, we encourage tool presentations. Depending on the number of submissions, long papers will be 20-30 minutes and short papers 15-20 minutes including Q&A. For the workshop we are expecting around 20-30 participants to attend. Should IJCAI 2021 be held online because of the COVID-19 situation, then we are willing to hold the workshop online.

All submitted papers must:

  • be written in English;
  • contain author names, affiliations, and email addresses;
  • be formatted according to the Springer LNCS template;
  • be in PDF (make sure that the PDF can be viewed on any platform).
sedami/start2021.txt · Last modified: 2022/05/08 22:11 by gjn
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0