Group online adaptive learning
Abstract
Sharing information among multiple learning agents can accelerate learning. It
could be particularly useful if learners operate in continuously changing environments, because
a learner could benefit from previous experience of another learner to adapt to their
new environment. Such group-adaptive learning has numerous applications, from predicting
financial time-series, through content recommendation systems, to visual understanding for
adaptive autonomous agents.
Here we address the problem in the context of online adaptive learning. We formally
define the learning settings of group online adaptive learning (GOAL) and derive an algorithm
(SOAL) to address it. SOAL avoids modeling explicitly or their dynamics, and instead
shares information continuously. The key idea is that learners share a common small pool of
experts, which they can use in a weighted adaptive way.We define group adaptive regret and
prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive
learners. Furthermore, it quickly adapts when presented with scenes that are related to
scenes shared by other learners.
We demonstrate the benefits of the approach for two domains: vision and text. First,
in the visual domain, we study a visual navigation task where a robot learns to navigate
based on outdoor video scenes. We show how navigation can improve when knowledge
from other robots in related scenes is available. Second, in the text domain, we create a new
dataset for the task of assigning submitted papers to relevant editors. This is, inherently,
an adaptive learning task due to the dynamic nature of research fields evolving in time.
We show how learning to assign editors improves when knowledge from other editors is
available. Together, these results demonstrate the benefits for sharing information across
learners in concurrently changing environments.