Bayesian Active Learning By Distribution Disagreement

ICLR 2025 Conference Submission9933 Authors

Keywords: Active Learning, Normalizing Flows, Regression, Uncertainty Quantification

TL;DR: We show that standard AL heuristics do not work well for AL with normalizing flows and propose an extension to BALD to remedy this.

Abstract:

Active Learning (AL) for regression has been systematically under-researched due to the increased difficulty of measuring uncertainty in regression models.
Since normalizing flows offer a full predictive distribution instead of a point forecast, they facilitate direct usage of known heuristics for AL like Entropy or Least-Confident sampling.
However, we show that most of these heuristics do not work well for normalizing flows in pool-based AL and we need more sophisticated algorithms to distinguish between aleatoric and epistemic uncertainty.
In this work we propose BALSA, an adaptation of the BALD algorithm, tailored for regression with normalizing flows.
With this work we extend current research on uncertainty quantification with normalizing flows to real world data and pool-based AL with multiple acquisition functions and query sizes.
We report SOTA results for BALSA across 4 different datasets and 2 different architectures.

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9933