Efficacy of Bayesian Neural Networks in Active Learning
This work addresses data labeling costs for machine learning practitioners, but it appears incremental as it builds on existing active learning methods.
The paper tackled the problem of expensive labeled data in machine learning by exploring Bayesian neural networks for active learning, showing they are more efficient than ensemble techniques in capturing uncertainty, though no concrete numbers were provided.
Obtaining labeled data for machine learning tasks can be prohibitively expensive. Active learning mitigates this issue by exploring the unlabeled data space and prioritizing the selection of data that can best improve the model performance. A common approach to active learning is to pick a small sample of data for which the model is most uncertain. In this paper, we explore the efficacy of Bayesian neural networks for active learning, which naturally models uncertainty by learning distribution over the weights of neural networks. By performing a comprehensive set of experiments, we show that Bayesian neural networks are more efficient than ensemble based techniques in capturing uncertainty. Our findings also reveal some key drawbacks of the ensemble techniques, which was recently shown to be more effective than Monte Carlo dropouts.