Meta-learning improvesgeneralization ofmachine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks.

Wedemonstratethattheproposed approach performs better than random selection, outperforming all other baselines, with performance comparable tosupervised approach using merely 10%annotations.

However, current approaches can only model distributions for which training samples are directly accessible, which is not the case in many real-world tasks.