Adaptive & Multitask Learning

Overview

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:

• advantages, disadvantages, and applicability of different approaches to learning in multitask settings,
• formal or intuitive connections between methods developed for different problems that help better understand multitask learning techniques and inspire technique transfer between research lines,
• fundamental challenges and open questions that the community needs to tackle for the field to move forward.