Scalable Batch Acquisition for Deep Bayesian Active Learning

Aleksandr Rubashevskii, Daria Kotova, Maxim Panov
1/13/2023
cs.LGstat.ML

No official code found. Best implementation: stat-ml/large_batch_bald (4 stars, Apache-2.0, last commit 2023-04-19).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

stat-ml/large_batch_baldCommunity100%
Apache-2.0

Scalable Batch Acquisition for Deep Bayesian Active Learning

41Python, Jupyter NotebookMay 18, 20223 years agoApache-2.0

Similar Papers

Big Batch Bayesian Active Learning by Considering Predictive Probabilities

85% match2025

Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning

84% match2023

Myopic Bayesian Decision Theory for Batch Active Learning with Partial Batch Label Sampling

82% match1 repo52025

Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification

81% match1 repo172024

ConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints

81% match2025

Black-Box Batch Active Learning for Regression

80% match1 repo72023

Cite this paper

@article{rubashevskii2023scalable,
  title  = {Scalable Batch Acquisition for Deep Bayesian Active Learning},
  author = {Aleksandr Rubashevskii and Daria Kotova and Maxim Panov},
  year   = {2023},
  eprint = {2301.05490},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.05490v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.05490.svg)](https://codeofpaper.com/paper/2301.05490)

Discussion