Active Learning Helps Pretrained Models Learn the Intended Task
This addresses the issue of unreliable model deployment for users by showing that pretraining enhances active learning efficiency, though it is incremental as it builds on existing active learning methods.
The paper tackles the problem of task ambiguity in machine learning, where models can fail unpredictably due to multiple behaviors being consistent with training data, and finds that pretrained models are better active learners, requiring up to 5 times fewer labels to disambiguate tasks compared to non-pretrained models.
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.