Bayesian Active Learning By Distribution Disagreement
This work addresses the problem of improving active learning efficiency in regression tasks for machine learning practitioners, though it is incremental as it adapts an existing algorithm to a specific model type.
The paper tackles the challenge of active learning for regression by proposing BALSA, an adaptation of the BALD algorithm tailored for normalizing flows, which achieves state-of-the-art results across 4 datasets and 2 architectures.
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 \cite{berry2023normalizing, berry2023escaping} 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.