Active Learning Helps Pretrained Models Learn the Intended Task

• Main Authors: Tamkin, Alex, Nguyen, Dat, Deshpande, Salil, Mu, Jesse, Goodman, Noah
• Format: Journal Article
• Language: English
• Published: 18-04-2022
• Subjects: Computer Science - Computation and Language; Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.2204.08491

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 pretraining process: pretrained models require up to 5 times fewer labels
when using uncertainty-based active learning, while non-pretrained models see
no or even negative benefit. We find these gains come from an ability to select
examples with attributes that disambiguate the intended behavior, such as rare
product categories or atypical backgrounds. These attributes are far more
linearly separable in pretrained model's representation spaces vs
non-pretrained models, suggesting a possible mechanism for this behavior.