Let the Model Decide its Curriculum for Multitask Learning. (arXiv:2205.09898v1 [cs.LG])

Curriculum learning strategies in prior multi-task learning approaches
arrange datasets in a difficulty hierarchy either based on human perception or
by exhaustively searching the optimal arrangement. However, human perception of
difficulty may not always correlate well with machine interpretation leading to
poor performance and exhaustive search is computationally expensive. Addressing
these concerns, we propose two classes of techniques to arrange training
instances into a learning curriculum based on difficulty scores computed via
model-based approaches. The two classes i.e Dataset-level and …

arxiv curriculum learning multitask learning