15. – 20. Juli 2018, Dagstuhl-Seminar 18291

Extreme Classification


Samy Bengio (Google Inc. – Mountain View, US)
Krzysztof Dembczynski (Poznan University of Technology, PL)
Thorsten Joachims (Cornell University – Ithaca, US)
Marius Kloft (TU Kaiserslautern, DE)
Manik Varma (Microsoft Research India – Bangalore, IN)

Auskunft zu diesem Dagstuhl-Seminar erteilt

Dagstuhl Service Team


Gemeinsame Dokumente


Extreme classification is a rapidly growing research area within machine learning focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications of extreme classification have been found in diverse areas ranging from language modeling to document tagging in NLP, face recognition to learning universal feature representations in computer vision, gene function prediction in bioinformatics, etc. Extreme classification has also opened up a new paradigm for key industrial applications such as ranking and recommendation by reformulating them as multi-label learning tasks where each item to be ranked or recommended is treated as a separate label. Such reformulations have led to significant gains over traditional collaborative filtering and content-based recommendation techniques. Consequently, extreme classifiers have been deployed in many real-world applications in industry.

Extreme classification raises a number of interesting research questions including those related to the following topics:

  • Algorithms for extreme classification
  • Theoretical foundations of extreme classification
  • Gathering techniques for supervised data
  • Long tail effects in machine learning
  • Deep learning for extreme classification
  • Counterfactual learning for extreme classification
  • Applications in advertising, bioinformatics, information retrieval, natural language processing, recommender systems, vision and other domains

This Dagstuhl Seminar on extreme classification aims to bring together researchers interested in these topics to encourage discussion, identify important problems and promising research directions, foster collaboration and improve upon the state-of-the-art. We hope to have a healthy mix of participants from both academia and industry as well as researchers from both core machine learning and applied areas such as recommender systems, computer vision, computational advertising, information retrieval and natural language processing.

  Creative Commons BY 3.0 DE
  Samy Bengio, Krzysztof Dembczynski, Thorsten Joachims, Marius Kloft, and Manik Varma

Related Dagstuhl-Seminar


  • Artificial Intelligence / Robotics
  • Computer Graphics / Computer Vision
  • Data Structures / Algorithms / Complexity


  • Algorithms and complexity
  • Machine learning
  • Artificial intelligence
  • Computer vision


Bücher der Teilnehmer 

Buchausstellung im Erdgeschoss der Bibliothek

(nur in der Veranstaltungswoche).


In der Reihe Dagstuhl Reports werden alle Dagstuhl-Seminare und Dagstuhl-Perspektiven-Workshops dokumentiert. Die Organisatoren stellen zusammen mit dem Collector des Seminars einen Bericht zusammen, der die Beiträge der Autoren zusammenfasst und um eine Zusammenfassung ergänzt.


Download Übersichtsflyer (PDF).


Es besteht weiterhin die Möglichkeit, eine umfassende Kollektion begutachteter Arbeiten in der Reihe Dagstuhl Follow-Ups zu publizieren.

Dagstuhl's Impact

Bitte informieren Sie uns, wenn eine Veröffentlichung ausgehend von
Ihrem Seminar entsteht. Derartige Veröffentlichungen werden von uns in der Rubrik Dagstuhl's Impact separat aufgelistet  und im Erdgeschoss der Bibliothek präsentiert.