Scalable Batch Acquisition for Deep Bayesian Active Learning
In deep active learning, it is especially important to choose multiple examples to markup at each step to work efficiently, especially on large datasets. At the same time, existing solutions to this problem in the Bayesian setup, such as BatchBALD, have significant limitations in selecting a large number of examples, associated with the exponential complexity of computing mutual information for joint random variables. We, therefore, present the Large BatchBALD algorithm, which gives a well-grounded approximation to the BatchBALD method that aims to achieve comparable quality while being more computationally efficient. We provide a complexity analysis of the algorithm, showing a reduction in computation time, especially for large batches. Furthermore, we present an extensive set of experimental results on image and text data, both on toy datasets and larger ones such as CIFAR-100.
Code (1)
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing
Active learning has demonstrated data efficiency in many fields. Existing active learning algorithms, especially in the context of batch-mode deep Bayesian active models, rely heavily on the quality of uncertainty estima…
Active LearningDiversityMulti-class ClassificationPowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions
We develop BatchEvaluationBALD, a new acquisition function for deep Bayesian active learning, as an expansion of BatchBALD that takes into account an evaluation set of unlabeled data, for example, the pool set. We also d…
Active LearningBatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task…
Active LearningConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints
Varying annotation costs among data points and budget constraints can hinder the adoption of active learning strategies in real-world applications. This work introduces two Bayesian active learning strategies for batch a…
Active LearningBig Batch Bayesian Active Learning by Considering Predictive Probabilities
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 obse…
Active Learning