analiza aiqbench
This survey reviews time series anomaly detection methods, including diffusion models, state space models, and LLM-based approaches, and proposes a taxonomy plus a benchmark repository. Its most useful contributions for practitioners are the metric-fidelity experiments and the open-source evaluation tools, since the authors argue that many reported gains depend on how anomalies are scored. Readers building monitoring or fault-detection systems should check how the benchmarks handle multivariate data and zero-shot transfer before relying on any single architecture.
Future of Time Series Anomaly Detection: From Historical Review to Unified Outlook
arXiv:2610.30628v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) is a foundational problem in data mining, aiming to identify observations that deviate significantly from nominal temporal patterns. Driven by escalating data volumes and application complexity, recent research has yielded diverse architectures, including diffusion models, state space models, and large language models (LLMs). However, existing surveys provide limited coverage of these emerging designs and lack a unified treatment of multivariate anomalies, cross-domain unified modeling, metric reliability, and contemporary evaluation challenges. To bridge these gaps, this survey delivers three core contributions: (1) We establish a refined anomaly categorization and a structured taxonomy of paradigms reflecting modern advances, comparing detection mechanisms and charting developmental trajectories across paradigms. (2) We provide an extensive analysis of evaluation methodologies and conduct comprehensive experiments to assess metric fidelity, complemented by an open-source benchmark repository encompassing algorithms, datasets, and evaluation tools. (3) We outline key open challenges, offering forward-looking perspectives on dynamic thresholding, model interpretability, zero-shot transfer, multi-modal alignment, and foundational models for time series. By addressing existing theoretical and empirical limitations, this survey establishes a coherent framework to guide future TSAD research and practical deployments.
Abstract:Time series anomaly detection (TSAD) is a foundational problem in data mining, aiming to identify observations that deviate significantly from nominal temporal patterns. Driven by escalating data volumes and application complexity, recent research has yielded diverse architectures, including diffusion models, state space models, and large language models (LLMs). However, existing surveys provide limited coverage of these emerging designs and lack a unified treatment of multivariate anomalies, cross-domain unified modeling, metric reliability, and contemporary evaluation challenges. To bridge these gaps, this survey delivers three core contributions: (1) We establish a refined anomaly categorization and a structured taxonomy of paradigms reflecting modern advances, comparing detection mechanisms and charting developmental trajectories across paradigms. (2) We provide an extensive analysis of evaluation methodologies and conduct comprehensive experiments to assess metric fidelity, complemented by an open-source benchmark repository encompassing algorithms, datasets, and evaluation tools. (3) We outline key open challenges, offering forward-looking perspectives on dynamic thresholding, model interpretability, zero-shot transfer, multi-modal alignment, and foundational models for time series. By addressing existing theoretical and empirical limitations, this survey establishes a coherent framework to guide future TSAD research and practical deployments.
18 pages, 5 figures, 4 tables. Accepted by IEEE Transactions on Artificial Intelligence. DOI: https://doi.org/10.1109/TAI.2026.3746935
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2610.30628 [cs.LG]
(or arXiv:2610.30628v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.30628 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1109/TAI.2026.3746935 Focus to learn more DOI(s) linking to related resources
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 · 306 cuvinte
Subiecte conexe
Article: Multi-Agent AI for Production Security Operations: an A2A and MCP Architecture in a 5G Core
InfoQ · 23 iul. 2026
Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection
arXiv · 1 sept. 2026
How Indegene is modernizing and scaling enterprise data quality in life sciences
AWS · 4 nov. 2026
When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense
arXiv · 24 sept. 2026