We observe that BatchBALD, a popular acquisition function for batch Bayesian active learning for classification, can conflate epistemic and aleatoric uncertainty, leading to suboptimal performance. Motivated by this observation, we propose to focus on the predictive probabilities, which only exhibit epistemic uncertainty. The result is an acquisition function that not only performs better, but is also faster to evaluate, allowing for larger batches than before.
@article{arxiv.2501.08223,
title = {Big Batch Bayesian Active Learning by Considering Predictive Probabilities},
author = {Sebastian W. Ober and Samuel Power and Tom Diethe and Henry B. Moss},
journal= {arXiv preprint arXiv:2501.08223},
year = {2025}
}
Comments
7 pages, 2 figures; presented as a lightning talk at the NeurIPS Workshop on Bayesian Decision-making and Uncertainty (BDU; 2024)