Unsupervised Anomaly Detection

Unsupervised Anomaly Detection is a methodological framework within anomaly detection that identifies rare or deviant patterns in data without relying on labeled instances, distinguishing itself from supervised and semi-supervised approaches by exclusively leveraging the intrinsic structure of unlabeled datasets to model normal behavior and flag outliers.

1.4K

Publications

88.2K

Citations

6.9K

Authors

1.4K

Institutions

Publications per year

2017–2026

1.1K

Authors

6.9K

  1. GP
    Guansong Pang

    Singapore Management University, Singapore

    11 publications · 868 citations

    11

    h-index

  2. DP
    Dan Pei

    Tsinghua University, China

    11 publications · 1.3K citations

    11

    h-index

  3. GA
    Gian Antonio Susto

    University of Padua, Italy

    8 publications · 529 citations

    9

    h-index

  4. CL
    Christopher Leckie

    The University of Melbourne, Australia

    9 publications · 558 citations

    9

    h-index

  5. MK
    Marius Kloft

    University of Kaiserslautern, Germany

    8 publications · 373 citations

    8

    h-index

1–5 of 6.9K

Venues

  1. arXiv (Cornell University)

    Repository · 90 publications · 3.7K citations

    33

    h-index

  2. IEEE Access

    42 publications · 3.1K citations

    31

    h-index

  3. Sensors

    21 publications · 803 citations

    19

    h-index

  4. 17

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 18 publications · 2.1K citations

    16

    h-index

1–5