Timezone: »

 
MetaDL: Few Shot Learning Competition with Novel Datasets from Practical Domains + Q&A
Adrian El Baz · Isabelle Guyon · Zhengying Liu · Jan N. Van Rijn · Haozhe Sun · Sébastien Treguer · Wei-Wei Tu · Ihsan Ullah · Joaquin Vanschoren · Phan Ahn Vu

Wed Dec 08 03:25 AM -- 03:45 AM (PST) @
in Competition Track Day 2: Overviews + Breakout Sessions »
Event URL: https://metalearning.chalearn.org »

Meta-learning is an important machine learning paradigm leveraging experience from previous tasks to make better predictions on the task at hand. This competition focuses on supervised learning, and more particularly `few shot learning' classification settings, aiming at learning a good model from very few examples, typically 1 to 5 per class. A starting kit will be provided, consisting of a public dataset and various baseline implementations, including MAML (Finn et al., 2017) and Prototypical Networks (Snell et al., 2017). This way, it should be easy to get started and build upon the various resources in the field. The competition consists of novel datasets from various domains, including healthcare, ecology, biology, and chemistry. The competition will consist of three phases: a public phase, a feedback phase, and a final phase. The last two phases will be run with code submissions, fully bind-tested on the Codalab challenge platform. A single (final) submission will be evaluated during the final phase, using five fresh datasets, currently unknown to the meta-learning community.

Author Information

Adrian El Baz (ChaLearn)
Isabelle Guyon (UPSud, INRIA, University Paris-saclay and ChaLearn)
Zhengying Liu (Inria/U. Paris-Saclay)
Jan N. Van Rijn (Leiden University)
Haozhe Sun (Paris-Saclay University)
Sébastien Treguer (INRIA / Chalearn)
Wei-Wei Tu (4Paradigm Inc.)
Ihsan Ullah (Université Paris Saclay)
Joaquin Vanschoren (Eindhoven University of Technology)
Phan Ahn Vu (Paris-Saclay University)

More from the Same Authors