“Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction performance for the target task due to negative transfers. Thus, a critical problem in multitask learning is identifying subsets of source tasks that would benefit the target task. … In this paper, we introduce an efficient procedure to address this problem via surrogate modeling.”

Find the paper and the full list of authors at ArXiv.