Extreme Multilabel Classification for Social Media

April 24, 2018, Lyon, France

XMLC for Social Media

Extreme Multilabel Classification (XMLC) is a very active and rapidly growing research area that deals with the problem of labeling an item with a small set of tags out of an extremely large number of potential tags. Applications include content understanding, document tagging, image tagging, biological sequence tagging, recommendation, etc. While the difficulty and the potential applications of XMLC are well understood in the core machine learning community, to the best of our knowledge, XMLC has not made inroads in the field of Information Retrieval (IR) and related areas. The aim of this workshop is to bring researchers from academia and industry in order to further advance this very exciting field and come up with potential applications of XMLC in new areas. We envision a gathering of researchers and practitioners either currently working on XMLC, or using XMLC algorithms for their products, or who may use XMLC in future. There would be invited talks from many renowned researchers in this area. We are also seeking extended abstracts and full papers (short and long) presenting interesting work in this direction for being accepted either as a spotlight talk, paper or poster. Given that we are soliciting new application areas for XMLC, we expect researchers from a variety of backgrounds: core ML, recommendations, applications of XMLC in video and image tagging, speech processing, IR etc.


  • Akshay Soni, Yahoo Research, Sunnyvale (akshaysoni@oath.com)
  • Robert Busa-Fekete, Yahoo Research, New York (busafekete@oath.com)
  • Krzysztof DembczyÅ„ski, Poznan University of Technology (kdembczynski@cs.put.poznan.pl)
  • Aasish Pappu, Yahoo Research, New York (aasishkp@oath.com)