Big Batch Bayesian Active Learning by Considering Predictive Probabilities
Abstract
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.
Cite
Text
Ober et al. "Big Batch Bayesian Active Learning by Considering Predictive Probabilities." NeurIPS 2024 Workshops: BDU, 2024.Markdown
[Ober et al. "Big Batch Bayesian Active Learning by Considering Predictive Probabilities." NeurIPS 2024 Workshops: BDU, 2024.](https://mlanthology.org/neuripsw/2024/ober2024neuripsw-big/)BibTeX
@inproceedings{ober2024neuripsw-big,
title = {{Big Batch Bayesian Active Learning by Considering Predictive Probabilities}},
author = {Ober, Sebastian W. and Power, Samuel and Diethe, Tom and Moss, Henry},
booktitle = {NeurIPS 2024 Workshops: BDU},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/ober2024neuripsw-big/}
}