Text Anomaly Detection with Simplified Isolation Kernel
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909983015174144 |
|---|---|
| author | Cao, Yang Yang, Sikun Yang, Yujiu Qi, Lianyong Liu, Ming |
| author_facet | Cao, Yang Yang, Sikun Yang, Yujiu Qi, Lianyong Liu, Ming |
| contents | Two-step approaches combining pre-trained large language model embeddings and anomaly detectors demonstrate strong performance in text anomaly detection by leveraging rich semantic representations. However, high-dimensional dense embeddings extracted by large language models pose challenges due to substantial memory requirements and high computation time. To address this challenge, we introduce the Simplified Isolation Kernel (SIK), which maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics. SIK has linear time complexity and significantly reduces space complexity through its innovative boundary-focused feature mapping. Experiments across 7 datasets demonstrate that SIK achieves better detection performance than 11 state-of-the-art (SOTA) anomaly detection algorithms while maintaining computational efficiency and low memory cost. All code and demonstrations are available at https://github.com/charles-cao/SIK. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text Anomaly Detection with Simplified Isolation Kernel Cao, Yang Yang, Sikun Yang, Yujiu Qi, Lianyong Liu, Ming Computation and Language Two-step approaches combining pre-trained large language model embeddings and anomaly detectors demonstrate strong performance in text anomaly detection by leveraging rich semantic representations. However, high-dimensional dense embeddings extracted by large language models pose challenges due to substantial memory requirements and high computation time. To address this challenge, we introduce the Simplified Isolation Kernel (SIK), which maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics. SIK has linear time complexity and significantly reduces space complexity through its innovative boundary-focused feature mapping. Experiments across 7 datasets demonstrate that SIK achieves better detection performance than 11 state-of-the-art (SOTA) anomaly detection algorithms while maintaining computational efficiency and low memory cost. All code and demonstrations are available at https://github.com/charles-cao/SIK. |
| title | Text Anomaly Detection with Simplified Isolation Kernel |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.13197 |