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

Hanyin Cheng, Ruitong Zhang, Yuning Lu, Peng Chen, Meng Wang, Yang Shu, Bin Yang, Chenjuan Guo

Keywords: Time Series Anomaly Detection

Abstract:

While Time Series Foundation Models (TSFMs) have demonstrated remarkable success in Multivariate Time Series Anomaly Detection (MTSAD), in real-world scenarios, many time series comprise not only \textit{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, and typically treat 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 **ST**ate-aware **A**dapte**R** (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 comprises three core innovative components: (1) *Identity-guided State Encoder* effectively captures the complex categorical semantics of state variables through a learnable *State Memory*. (2) *Conditional Bottleneck Adapter* dynamically generates low-rank adaptation parameters conditioned on the current state, thereby flexibly injecting the influence of state variables into the backbone model. (3) *Numeral-State Matching* module effectively detects 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.

Primary Area: learning on time series and dynamical systems

Submission Number: 7325