Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.07863 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908699131379712 |
|---|---|
| author | Gao, Jianling Tao, Chongyang Lin, Xuelian Liu, Junfeng Ma, Shuai |
| author_facet | Gao, Jianling Tao, Chongyang Lin, Xuelian Liu, Junfeng Ma, Shuai |
| contents | Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or pair-centric} view not only overlooks the contextual nature of anomalies, which are defined by their deviation from a collective group, but also fails to exploit the rich supervisory signals that can be generated from the combinatorial composition of sets. Consequently, such models struggle to exploit the high-order interactions within the data, which are critical for learning discriminative representations. To address these limitations, we propose SetAD, a novel framework that reframes semi-supervised AD as a Set-level Anomaly Detection task. SetAD employs an attention-based set encoder trained via a graded learning objective, where the model learns to quantify the degree of anomalousness within an entire set. This approach directly models the complex group-level interactions that define anomalies. Furthermore, to enhance robustness and score calibration, we propose a context-calibrated anomaly scoring mechanism, which assesses a point's anomaly score by aggregating its normalized deviations from peer behavior across multiple, diverse contextual sets. Extensive experiments on 10 real-world datasets demonstrate that SetAD significantly outperforms state-of-the-art models. Notably, we show that our model's performance consistently improves with increasing set size, providing strong empirical support for the set-based formulation of anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07863 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SetAD: Semi-Supervised Anomaly Learning in Contextual Sets Gao, Jianling Tao, Chongyang Lin, Xuelian Liu, Junfeng Ma, Shuai Machine Learning Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or pair-centric} view not only overlooks the contextual nature of anomalies, which are defined by their deviation from a collective group, but also fails to exploit the rich supervisory signals that can be generated from the combinatorial composition of sets. Consequently, such models struggle to exploit the high-order interactions within the data, which are critical for learning discriminative representations. To address these limitations, we propose SetAD, a novel framework that reframes semi-supervised AD as a Set-level Anomaly Detection task. SetAD employs an attention-based set encoder trained via a graded learning objective, where the model learns to quantify the degree of anomalousness within an entire set. This approach directly models the complex group-level interactions that define anomalies. Furthermore, to enhance robustness and score calibration, we propose a context-calibrated anomaly scoring mechanism, which assesses a point's anomaly score by aggregating its normalized deviations from peer behavior across multiple, diverse contextual sets. Extensive experiments on 10 real-world datasets demonstrate that SetAD significantly outperforms state-of-the-art models. Notably, we show that our model's performance consistently improves with increasing set size, providing strong empirical support for the set-based formulation of anomaly detection. |
| title | SetAD: Semi-Supervised Anomaly Learning in Contextual Sets |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.07863 |