Batch Active Learning

Batch Active Learning is a variant of active learning in which a batch of multiple unlabeled instances is selected simultaneously for annotation in each query iteration, as opposed to selecting instances one at a time, thereby balancing informativeness and diversity while reducing the number of model retraining cycles.

174

Publications

11.3K

Citations

487

Authors

219

Institutions

Publications per year

2017–2026

90

Variants

Batch-mode Active Learning

Authors

487

  1. SP
    Sethuraman Panchanathan

    Arizona State University, United States

    9 publications · 434 citations

    9

    h-index

  2. SC
    Steven C. H. Hoi

    Nanyang Technological University, Singapore

    7 publications · 1.1K citations

    7

    h-index

  3. SC
    Shayok Chakraborty

    Arizona State University, United States

    7 publications · 264 citations

    7

    h-index

  4. JY
    Jieping Ye

    Arizona State University, United States

    6 publications · 458 citations

    6

    h-index

  5. VN
    Vineeth N Balasubramanian

    Indian Institute of Technology Hyderabad, India

    5 publications · 202 citations

    5

    h-index

1–5 of 487

Venues

  1. arXiv (Cornell University)

    Repository · 23 publications · 1.9K citations

    17

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 7 publications · 190 citations

    7

    h-index

  3. Neurocomputing

    7 publications · 204 citations

    7

    h-index

  4. 5

    h-index

  5. Information Sciences

    4 publications · 304 citations

    4

    h-index

1–5