Publication Type
Journal Article
Version
acceptedVersion
Publication Date
9-2023
Abstract
Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly contamination) may mislead the learning process when all the unlabeled data are employed as inliers for model training; 2) only discrete supervision information (such as binary or ordinal data labels) is exploited, which leads to suboptimal learning of anomaly scores that essentially take on a continuous distribution. Therefore, this paper proposes a novel semi-supervised anomaly detection method, which devises contamination-resilient continuous supervisory signals. Specifically, we propose a mass interpolation method to diffuse the abnormality of labeled anomalies, thereby creating new data samples labeled with continuous abnormal degrees. Meanwhile, the contaminated area can be covered by new data samples generated via combinations of data with correct labels. A feature learning based objective is added to serve as an optimization constraint to regularize the network and further enhance the robustness w.r.t. anomaly contamination. Extensive experiments on 11 real world datasets show that our approach significantly outperforms state-of-the-art competitors by 20%-30% in AUC-PR and obtains more robust and superior performance in settings with different anomaly contamination levels and varying numbers of labeled anomalies.
Keywords
Anomaly detection, Anomaly contamination, Continuous supervision, Semi-supervised learning, Deep learning
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
Information Processing and Management
Volume
60
Issue
5
First Page
1
Last Page
17
ISSN
0306-4573
Identifier
10.1016/j.ipm.2023.103459
Publisher
Elsevier
Citation
XU, Hongzuo; WANG, Yijie; PANG, Guansong; JIAN, Songlei; LIU, Ning; and WANG, Yongjun.
RoSAS: Deep semi-supervised anomaly detection with contamination-resilient continuous supervision. (2023). Information Processing and Management. 60, (5), 1-17.
Available at: https://ink.library.smu.edu.sg/sis_research/8267
Copyright Owner and License
Authors-CC-BY
Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.
Additional URL
https://doi.org/10.1016/j.ipm.2023.103459