[Corpora-List] CFP: IJCAI 2016 First Workshop on Human is More Than a Labeler (BeyondLabeler)

John Carroll J.A.Carroll at sussex.ac.uk
Wed Apr 13 13:36:18 CEST 2016


==================================================================== IJCAI 2016 Workshop: Human is More Than a Labeler (BeyondLabeler) New York City, New York, USA http://smileclinic.alwaysdata.net/ijcai16workshop/ ====================================================================

Important Dates ----------------------------------------------------------------------

Paper submission deadline: April 30 2016 Notification of acceptance: May 18 2016 Camera-ready submission deadline: June 10 2016 BeyondLabeler workshop at IJCAI 2016 in NYC: July 10 2016

Invited Speakers ----------------------------------------------------------------------

Vladimir Vapnik, Facebook AI Research Alan Fern, Oregon State University Rogerio Feris, IBM T.J. Watson Research Michael Littman, Brown University Rich Caruana, Microsoft Research

Overview ----------------------------------------------------------------------

Can we better classify objects in images with labeled examples plus a textual description of the object per image? Or will it be also better with labeled examples plus a collection of rules that can be used to prove whether or not an object is a member of a particular class? Or how about improving the performance of learning systems via user interactions? The main purpose of our proposed "First Workshop on Human is More Than a Labeler (BeyondLabeler)" is to bring together researchers and practitioners who are working to instill more than label annotations into their machine learning algorithms.

Learning in those scenarios has been conceptualized as far back as 1990s and as recent as 2009. Some examples include knowledge-based learning, learning using privileged information (LUPI), learning with hints, interactive learning, multi-view learning, multi-task learning, model compression/distillation, reinforcement learning with guidance, and active and co-active learning for problem solving. This learning framework is commonly seen in a variety of application fields including natural language processing, computer vision, and medical informatics, to name a few.

Topics ----------------------------------------------------------------------

The main goal of this workshop is to have discussion on the following non-exhaustive topics: - What are the similarities and differences among all existing learning concepts that try to incorporate information beyond label annotations? - Is there an opportunity for a hybrid system ensembling state-of-the-art BeyondLabeller learning methods? - What are other novel application areas for this learning with labels plus additional information? - What if the additional information is wrong or inconsistent with the label annotations? - Will random additional information be helpful to improve the performance of the learning system?

Submission Details ----------------------------------------------------------------------

We encourage contributions either a technical paper (IJCAI style, 6 pages without references), a position statement (IJCAI style, 2 pages maximum), or a published work related to the workshop, clearly indicating in the paper that this is published work. Papers submission is via the Easychair system (https://easychair.org/conferences/?conf=beyondlabeler2016). Papers will be subject to a single-blind peer review, i.e. authors can keep their names and affiliations on their submitted papers. We are in touch with prominent ML journals to explore the idea of a special issue on this topic.

There will also be a Best Paper Award for the top quality submitted work, courtesy of our sponsors.

Program Committee ----------------------------------------------------------------------

Jude W. Shavlik, University of Wisconsin-Madison Prasad Tadepalli, Oregon State University Bernt Schiele, Max Planck Institute for Informatics Gautam Kunapuli, UtopiaCompression Corporation Christoph Lampert, IST Austria Andrea Passerini, University of Trento Pietro Galliani, University of Sussex Daniel Hernandez-Lobato, Universidad Autonoma de Madrid Emilie Morvant, Universite Jean Monnet Vijay Badrinarayanan, Magic Leap David Lopez-Paz, University of Cambridge Kshitij Judah, Oregon State University Tushar Khot, Allen Institute for Artificial Intelligence Karthik Raman, Google Phillip Odom, Indiana University Martin Mladenov, TU Dortmund Joseph Taylor, University of Sussex

Sponsors ----------------------------------------------------------------------

German Association for Pattern Recognition (DAGM) IBM Research Google

Organizers ----------------------------------------------------------------------

Sriraam Natarajan, Indiana University Novi Quadrianto, University of Sussex Kristian Kersting, TU Dortmund Rauf Izmailov, Vencore Labs Jana Doppa, Washington State University Viktoriia Sharmanska, University of Sussex

Contact: Novi Quadrianto at n.quadrianto at sussex.ac.uk



More information about the Corpora mailing list