Towards Task Sampler Learning for Meta-Learning

arXiv:2307.08924v3 Announce Type: replace
Abstract: Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning models. However, this paper challenges this view through empirical and theoretical analysis. We obtain three conclusions: (i) there is no universal task sampling strategy that can guarantee the optimal performance of meta-learning models; (ii) over-constraining task diversity may incur …

abstract analysis arxiv challenges cs.cv cs.lg data diverse diversity general knowledge learn meta meta-learning paper tasks through training transfer type view will