STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Hanyin, Zhang, Ruitong, Lu, Yuning, Chen, Peng, Wang, Meng, Shu, Yang, Yang, Bin, Guo, Chenjuan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866914100668268544
author	Cheng, Hanyin Zhang, Ruitong Lu, Yuning Chen, Peng Wang, Meng Shu, Yang Yang, Bin Guo, Chenjuan
author_facet	Cheng, Hanyin Zhang, Ruitong Lu, Yuning Chen, Peng Wang, Meng Shu, Yang Yang, Bin Guo, Chenjuan
contents	While Time Series Foundation Models (TSFMs) have demonstrated remarkable success in Multivariate Time Series Anomaly Detection (MTSAD), however, in real-world industrial scenarios, many time series comprise not only numerical variables such as temperature and flow, but also numerous discrete state variables that describe the system status, such as valve on/off or day of the week. Existing TSFMs often overlook the distinct categorical nature of state variables and their critical role as conditions, typically treating them uniformly with numerical variables. This inappropriate modeling approach prevents the model from fully leveraging state information and even leads to a significant degradation in detection performance after state variables are integrated. To address this critical limitation, this paper proposes a novel STate-aware AdapteR (STAR). STAR is a plug-and-play module designed to enhance the capability of TSFMs in modeling and leveraging state variables during the fine-tuning stage. Specifically, STAR comprisesthree core components: (1) We design an Identity-guided State Encoder, whicheffectively captures the complex categorical semantics of state variables through a learnable State Memory. (2) We propose a Conditional Bottleneck Adapter, which dynamically generates low-rank adaptation parameters conditioned on the current state, thereby flexibly injecting the influence of state variables into the backbone model. (3) We also introduce a Numeral-State Matching module to more effectively detect anomalies inherent to the state variables themselves. Extensive experiments conducted on real-world datasets demonstrate that STAR can improve the performance of existing TSFMs on MTSAD.
format	Preprint
id	arxiv_https___arxiv_org_abs_2510_16014
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter Cheng, Hanyin Zhang, Ruitong Lu, Yuning Chen, Peng Wang, Meng Shu, Yang Yang, Bin Guo, Chenjuan Machine Learning While Time Series Foundation Models (TSFMs) have demonstrated remarkable success in Multivariate Time Series Anomaly Detection (MTSAD), however, in real-world industrial scenarios, many time series comprise not only numerical variables such as temperature and flow, but also numerous discrete state variables that describe the system status, such as valve on/off or day of the week. Existing TSFMs often overlook the distinct categorical nature of state variables and their critical role as conditions, typically treating them uniformly with numerical variables. This inappropriate modeling approach prevents the model from fully leveraging state information and even leads to a significant degradation in detection performance after state variables are integrated. To address this critical limitation, this paper proposes a novel STate-aware AdapteR (STAR). STAR is a plug-and-play module designed to enhance the capability of TSFMs in modeling and leveraging state variables during the fine-tuning stage. Specifically, STAR comprisesthree core components: (1) We design an Identity-guided State Encoder, whicheffectively captures the complex categorical semantics of state variables through a learnable State Memory. (2) We propose a Conditional Bottleneck Adapter, which dynamically generates low-rank adaptation parameters conditioned on the current state, thereby flexibly injecting the influence of state variables into the backbone model. (3) We also introduce a Numeral-State Matching module to more effectively detect anomalies inherent to the state variables themselves. Extensive experiments conducted on real-world datasets demonstrate that STAR can improve the performance of existing TSFMs on MTSAD.
title	STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter
topic	Machine Learning
url	https://arxiv.org/abs/2510.16014