Mixture of basis for interpretable continual learning with distribution shifts. (arXiv:2201.01853v1 [cs.LG])

Continual learning in environments with shifting data distributions is a
challenging problem with several real-world applications. In this paper we
consider settings in which the data distribution(task) shifts abruptly and the
timing of these shifts are not known. Furthermore, we consider a
semi-supervised task-agnostic setting in which the learning algorithm has
access to both task-segmented and unsegmented data for offline training. We
propose a novel approach called mixture of Basismodels (MoB) for addressing
this problem setting. The core idea is …

arxiv distribution learning