Big Batch Bayesian Active Learning by Considering Predictive Probabilities
This work addresses a specific bottleneck in batch Bayesian active learning for classification, offering an incremental improvement.
The paper tackled the issue of BatchBALD conflating epistemic and aleatoric uncertainty in batch Bayesian active learning for classification, resulting in an acquisition function based on predictive probabilities that improves performance and enables faster evaluation with larger batches.
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.