arXiv：cs.LG· Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol·· 4 小时前
RAMSAD：基于相似度检索的时间序列异常检测模型选择框架
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
AI 导读
研究者提出 RAMSAD，一种基于检索的时间序列异常检测模型选择框架：给定新序列，从历史实例知识库中检索 top-k 最相似序列，并迁移其性能画像中的检测器推荐。该方法支持标准相似度度量与嵌入向量表示，在 ID 设置下优于现有基线，在 OOD 设置下最为稳健，仅选少量检测器即可匹敌或超越运行全部检测器的集成方案，成本仅为后者一小部分。
正文
Abstract:Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Our results show that RAMSAD outperforms existing baselines in In-Distribution (ID) settings and is the most robust selector in OOD, where, when selecting a small subset of detectors, it matches or exceeds ensembles that run the entire detector pool, at a fraction of their cost. Overall, we demonstrate that similarity-based retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.20243 [cs.LG] |
| (or arXiv:2610.20243v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20243 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Christos Panourgias [view email]
[v1]
Wed, 14 Oct 2026 14:18:55 UTC (1,358 KB)
来源：arXiv：cs.LG · arxiv.org