Active Learning Helps Pretrained Models Learn the Intended Task. (arXiv:2204.08491v1 [cs.LG])

Models can fail in unpredictable ways during deployment due to task
ambiguity, when multiple behaviors are consistent with the provided training
data. An example is an object classifier trained on red squares and blue
circles: when encountering blue squares, the intended behavior is undefined. We
investigate whether pretrained models are better active learners, capable of
disambiguating between the possible tasks a user may be trying to specify.
Intriguingly, we find that better active learning is an emergent property of
the …

active learning arxiv learning