Driven by progress in deep learning, the machine learning community is now able to tackle increasingly more complex problems—ranging from multi-modal reasoning to dexterous robotic manipulation—all of which typically involve solving nontrivial combinations of tasks. We believe that designing adaptive models and algorithms that can efficiently learn, master, and combine multiple tasks is the next frontier.
Establishing connections between approaches developed for seemingly different problems is particularly useful for analyzing the landscape of multitask learning techniques. For instance, the compositionality of language tasks motivates modular architectures, which can also be used to construct modular policies in order to tackle the compositional structure of robotic manipulation. Similarly, ideas from personalization in recommender systems (where serving different users can be regarded as different tasks) might perhaps be effective when applied to learning problems in healthcare or when used for adapting controllers in fleets of autonomous vehicles.
AMTL workshop aims to bring together machine learning researchers from areas ranging from theory to applications and systems, to explore and discuss:
June 17: Thanks to all contributors and organizers of #AMTL2019! Video recordings of the talks are now linked in the schedule.
June 5: Accepted papers and the tentative schedule are now up online.
May 7: Paper submission will remain open until May 14.
May 2: Application for travel grants is open. Apply before June 1.
April 30: Submissions will be extended until early May.
April 26: Exceptional contributions will be recognized with awards. Thanks to our fantastic sponsors!
April 8: Submission is open.
March 29: Call for papers is posted.
Paper submission: OpenReview (the review process is double-blind).
We invite the submission of short papers, up to 4 pages (excluding reference and supplementary material). Papers should be in ICML 2019 format (see the official style guidelines). For relevant topics and more details, see Call for Papers.
(Stanford)
(CMU, Determined AI)
(Tesla)
(Stanford, Berkeley, Google)
(UW, AI2)
(Netflix)
(UCL, IIT)
(Microsoft)