Abstract:Unsupervised anomaly detection of multivariate time series is a challenging task, given the requirements of deriving a compact detection criterion without accessing the anomaly points. The existing methods are mainly based on reconstruction error or association divergence, which are both confined to isolated subsequences with limited horizons, hardly promising unified series-level criterion. In this paper, we propose the Global Dictionary-enhanced Transformer (GDformer) with a renovated dictionary-based cross attention mechanism to cultivate the global representations shared by all normal points in the entire series. Accordingly, the cross-attention maps reflect the correlation weights between the point and global representations, which naturally leads to the representation-wise similarity-based detection criterion. To foster more compact detection boundary, prototypes are introduced to capture the distribution of normal point-global correlation weights. GDformer consistently achieves state-of-the-art unsupervised anomaly detection performance on five real-world benchmark datasets. Further experiments validate the global dictionary has great transferability among various datasets.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2501.18196 [cs.LG] |
| (or arXiv:2501.18196v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2501.18196 arXiv-issued DOI via DataCite |
From: Qingxiang Liu [view email]
[v1]
Thu, 30 Jan 2025 08:22:51 UTC (590 KB)
[v2]
Fri, 9 May 2025 09:25:21 UTC (449 KB)
[v3]
Sun, 24 May 2026 06:53:10 UTC (834 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。