SAformer: A time series anomaly detection model based on Similarity-Aware attention.
Saved in:
| Title: | SAformer: A time series anomaly detection model based on Similarity-Aware attention. |
|---|---|
| Authors: | Tang, Yunkai1 (AUTHOR) tangyk@cug.edu.cn, Li, Guiling1,2 (AUTHOR) guiling@cug.edu.cn, Wu, Zongda3 (AUTHOR) zongda1983@163.com, Yu, Philip S.4 (AUTHOR) psyu@uic.edu |
| Source: | Knowledge-Based Systems. Jun2026, Vol. 344, pN.PAG-N.PAG. 1p. |
| Subjects: | Outlier detection, Deep learning, Pattern perception |
| Abstract: | Time series anomaly detection has become a prominent research topic in recent years. Reconstruction-based methods have demonstrated strong performance on this task. However, existing approaches still struggle to detect shapelet anomalies and multi-peaked anomalies, as traditional attention mechanisms fail to comprehensively capture potential abnormal patterns. To address this limitation, we propose SAformer , a novel time series anomaly detection model based on S imilarity- A ware attention. SAformer incorporates shape similarity between subsequences to enhance traditional attention mechanisms and leverages a global dictionary to improve the detection of multi-peaked anomalies. In addition, it introduces the concepts of strong and weak similarity domains to further enrich similarity representation, while integrating sequence-level information to refine anomaly scores. Experimental results on five public benchmark datasets demonstrate that SAformer achieves state-of-the-art performance in anomaly detection, validating the effectiveness and robustness of the proposed SAformer attention mechanism. • SAformer fuses inter-subsequence similarity with Transformer. • Similarity-guided loss regulates attention patterns for effective learning. • Sequence-level information ensures sensitive anomaly scoring. • Extensive experiments on real datasets validate the model's effectiveness. [ABSTRACT FROM AUTHOR] |
| Copyright of Knowledge-Based Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193804164 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: SAformer: A time series anomaly detection model based on Similarity-Aware attention. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tang%2C+Yunkai%22">Tang, Yunkai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> tangyk@cug.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Guiling%22">Li, Guiling</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> guiling@cug.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Zongda%22">Wu, Zongda</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> zongda1983@163.com</i><br /><searchLink fieldCode="AR" term="%22Yu%2C+Philip+S%2E%22">Yu, Philip S.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> psyu@uic.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Knowledge-Based+Systems%22">Knowledge-Based Systems</searchLink>. Jun2026, Vol. 344, pN.PAG-N.PAG. 1p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Outlier+detection%22">Outlier detection</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Pattern+perception%22">Pattern perception</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Time series anomaly detection has become a prominent research topic in recent years. Reconstruction-based methods have demonstrated strong performance on this task. However, existing approaches still struggle to detect shapelet anomalies and multi-peaked anomalies, as traditional attention mechanisms fail to comprehensively capture potential abnormal patterns. To address this limitation, we propose SAformer , a novel time series anomaly detection model based on S imilarity- A ware attention. SAformer incorporates shape similarity between subsequences to enhance traditional attention mechanisms and leverages a global dictionary to improve the detection of multi-peaked anomalies. In addition, it introduces the concepts of strong and weak similarity domains to further enrich similarity representation, while integrating sequence-level information to refine anomaly scores. Experimental results on five public benchmark datasets demonstrate that SAformer achieves state-of-the-art performance in anomaly detection, validating the effectiveness and robustness of the proposed SAformer attention mechanism. • SAformer fuses inter-subsequence similarity with Transformer. • Similarity-guided loss regulates attention patterns for effective learning. • Sequence-level information ensures sensitive anomaly scoring. • Extensive experiments on real datasets validate the model's effectiveness. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Knowledge-Based Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193804164 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.knosys.2026.116087 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: N.PAG Subjects: – SubjectFull: Outlier detection Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Pattern perception Type: general Titles: – TitleFull: SAformer: A time series anomaly detection model based on Similarity-Aware attention. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tang, Yunkai – PersonEntity: Name: NameFull: Li, Guiling – PersonEntity: Name: NameFull: Wu, Zongda – PersonEntity: Name: NameFull: Yu, Philip S. IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 09507051 Numbering: – Type: volume Value: 344 Titles: – TitleFull: Knowledge-Based Systems Type: main |
| ResultId | 1 |
