Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

ICLR 2020 Shell Xu HuPablo G. MorenoYang XiaoXi ShenGuillaume ObozinskiNeil D. LawrenceAndreas Damianou

We propose a meta-learning approach that learns from multiple tasks in a transductive setting, by leveraging the unlabeled query set in addition to the support set to generate a more powerful model for each task. To develop our framework, we revisit the empirical Bayes formulation for multi-task learning... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.