TSAD: Transformer-Based Semi-Supervised Anomaly Detection for Dynamic Graphs

Jin Zhang and Ke Feng ()
Additional contact information
Jin Zhang: Party School of the CPC Hubei Provincial Committee, Wuhan 432200, China
Ke Feng: School of Economics, Peking University, Beijing 100871, China

Mathematics, 2025, vol. 13, issue 19, 1-21

Abstract: Anomaly detection aims to identify abnormal instances that significantly deviate from normal samples. With the natural connectivity between instances in the real world, graph neural networks have become increasingly important in solving anomaly detection problems. However, existing research mainly focuses on static graphs, while there is less research on mining anomaly patterns in dynamic graphs, which has important application value. This paper proposes a Transformer-based semi-supervised anomaly detection framework for dynamic graphs. The framework adopts the Transformer architecture as the core encoder, which can effectively capture long-range dependencies and complex temporal patterns between nodes in dynamic graphs. By introducing time-aware attention mechanisms, the model can adaptively focus on important information at different time steps, thereby better understanding the evolution process of graph structures. The multi-head attention mechanism of Transformer enables the model to simultaneously learn structural and temporal features of nodes, while positional encoding helps the model understand periodic patterns in time series. Comprehensive experiments on three real datasets show that TSAD significantly outperforms existing methods in anomaly detection accuracy, particularly demonstrating excellent performance in label-scarce scenarios.

Keywords: anomaly detection; dynamic graphs; multi-head attention; semi-supervised learning; graph neural networks (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/19/3123/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/19/3123/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:19:p:3123-:d:1761574

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().