Beyond Adaptation: Understanding Distributional Changes (Dagstuhl Seminar 20372)

Authors Georg Krempl, Vera Hofer, Geoffrey Webb, Eyke Hüllermeier and all authors of the abstracts in this report

Thumbnail PDF


  • Filesize: 2.56 MB
  • 36 pages

Document Identifiers

Author Details

Georg Krempl
  • Algorithmic Data Analysis, Department of Information and Computing Sciences, Utrecht University, The Netherlands
Vera Hofer
  • Department of Statistics and Operations Research, Karl-Franzens-University Graz, Austria
Geoffrey Webb
  • Data Science, Monash University, Australia
Eyke Hüllermeier
  • Intelligent Systems and Machine Learning, Paderborn University, Germany
and all authors of the abstracts in this report

Cite AsGet BibTex

Georg Krempl, Vera Hofer, Geoffrey Webb, and Eyke Hüllermeier. Beyond Adaptation: Understanding Distributional Changes (Dagstuhl Seminar 20372). In Dagstuhl Reports, Volume 10, Issue 4, pp. 1-36, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)


This report documents the program and the outcomes of Dagstuhl Seminar 20372 "Beyond Adaptation: Understanding Distributional Changes". It was centered around the aim to establish a better understanding of the causes, nature and consequences of distributional changes. Four key research questions were identified and discussed in during the seminar. These were the practical relevance of different scenarios and types of change, the modelling of change, the detection and measuring of change, and the adaptation to change. The seminar brought together participants from several distinct communities in which parts of these questions are already studied, albeit in separate lines of research. These included data stream mining, where the focus is on concept drift detection and adaptation, transfer learning and domain adaptation in machine learning and algorithmic learning theory, change point detection in statistics, and the evolving and adaptive systems community. Therefore, this seminar contributed to stimulate research towards a thorough understanding of distributional changes.

Subject Classification

ACM Subject Classification
  • Theory of computation → Machine learning theory
  • Mathematics of computing → Time series analysis
  • Computing methodologies → Multi-task learning
  • Computing methodologies → Learning under covariate shift
  • Computing methodologies → Lifelong machine learning
  • Statistical Machine Learning
  • Data Streams
  • Concept Drift
  • Non-Stationary Non-IID Data
  • Change Mining
  • Dagstuhl Seminar


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail