analiza aiqbench
This research introduces ONESHOT, a label-efficient method for time series anomaly detection that dynamically weights a pool of detectors using only a single confirmed anomaly. By leveraging operator-confirmed alerts to score and weight models, the approach effectively adapts to specific data series without requiring extensive labeled datasets. The study demonstrates significant performance gains over static selection or averaging strategies across diverse univariate and multivariate benchmarks.
OneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection
arXiv:2610.16219v1 Announce Type: new Abstract: Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore either select one detector for each series or average a pool of them. However, both assume that no label ever arrives, while a deployed monitor does receive them, since an operator confirms the alarms it raises. In this paper, we propose ONESHOT, which uses a single confirmed anomaly to weight the pool rather than to choose one detector from it. Specifically, we score each detector on the confirmed anomaly, and those scores become the weights of a soft mixture over the whole pool. We show that a single confirmed anomaly is enough to come close to the best detector for the series. Across 152 univariate and 73 multivariate series, ONESHOT outperforms the strongest single detector, averaging the whole pool, and even picking the best detector on the confirmed event. Code is available at: https://github.com/seunghan96/one_shot.
Abstract:Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore either select one detector for each series or average a pool of them. However, both assume that no label ever arrives, while a deployed monitor does receive them, since an operator confirms the alarms it raises. In this paper, we propose ONESHOT, which uses a single confirmed anomaly to weight the pool rather than to choose one detector from it. Specifically, we score each detector on the confirmed anomaly, and those scores become the weights of a soft mixture over the whole pool. We show that a single confirmed anomaly is enough to come close to the best detector for the series. Across 152 univariate and 73 multivariate series, ONESHOT outperforms the strongest single detector, averaging the whole pool, and even picking the best detector on the confirmed event. Code is available at: this https URL.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2610.16219 [cs.AI]
(or arXiv:2610.16219v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.16219 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 259 cuvinte
Subiecte conexe
[AINews] Gemini 4 Argon: GDM’s answer to Astra/Fable, with 1M output
Latent Space · 1 oct. 2026
Real-Time Intelligence with IBM Time Series Models on Confluent
Hugging Face · 2 sept. 2026
What We Learned Trying to Catch AI Liars: An Aletheia's Quest Retrospective
EleutherAI · 25 aug. 2026
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
arXiv · 15 oct. 2026