Big Batch Bayesian Active Learning by Considering Predictive Probabilities

Ober, Sebastian W and Power, Samuel and Diethe, Tom and Moss, Henry (2024) Big Batch Bayesian Active Learning by Considering Predictive Probabilities. In: Workshop on Bayesian Decision-making and Uncertainty, 38th Conference on Neural Information Processing Systems (NeurIPS 2024). :. UNSPECIFIED.

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.