LEARN-TS：基于正态性引导的LLM增强对齐与重构用于多元时间序列异常检测
LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection
浏览论文内容
中文总结 AI 辅助
LEARN-TS利用冻结语言模型构建角色分离的语义表示，通过窗口特定观测语义和固定正态性提示指导掩码重构，实现无需外部文本的多元时间序列异常检测，在四个基准上取得领先性能。
中文摘要 AI 辅助
在多元时间序列异常检测中，重构误差可能无法可靠地区分异常行为与良性偏差。语言衍生的语义提供了互补的上下文，但现有的多模态方法可能依赖于与时间关联的配对文本信息，这些信息难以一致地获取，并且标准多元时间序列异常检测基准并不提供此类信息。这一设定带来了两个挑战：（1）在不暴露精确数值目标或异常特定线索的情况下，将掩码重构条件化于窗口特定语义；（2）将窗口无关的正态性概念用作互补的语义参考，而非独立的异常检测器。我们提出了时间序列的LLM增强对齐与重构及正态性引导方法（LEARN-TS），该方法使用冻结的语言模型构建两种角色分离的语义表示，而无需时间配对的文本。窗口特定的观测语义编码了时间和跨变量上下文，但不包含精确数值，以指导通道共享的补丁掩码重构。一个固定的、与数据集无关的正态性提示提供了窗口无关的语义参考，用于对齐正常表示并估计正态性差异。在推理时，对每个时间补丁进行一次掩码，产生时间戳级别的重构证据，并由来自独立未掩码视图的差异进行条件调制。在四个基准上，LEARN-TS在16个数据集-指标比较中的13个中取得了最高的平均性能。受控消融实验考察了观测条件化、联合正态性对齐与评分以及参考内容，显示了数据集相关的排名提升以及语义参考相对于随机参考的适度平均增益。
英文摘要
Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations. Language-derived semantics offer complementary context, but existing multimodal approaches may rely on time-associated paired textual information that is difficult to obtain consistently and is not provided by standard multivariate time-series anomaly detection benchmarks. This setting poses two challenges: (1) conditioning masked reconstruction on window-specific semantics without exposing exact numerical targets or anomaly-specific cues, and (2) using a window-independent concept of normality as a complementary semantic reference rather than an independent anomaly detector. We propose LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Time Series (LEARN-TS), which uses a frozen language model to construct two role-separated semantic representations without requiring temporally paired external text. Window-specific observation semantics encode temporal and cross-variable context without exact numerical values to guide channel-shared patch-masked reconstruction. A fixed, dataset-agnostic normality prompt provides a window-independent semantic reference for aligning normal representations and estimating normality discrepancy. At inference, masking each temporal patch once yields timestamp-level reconstruction evidence, conditionally modulated by discrepancy from a separate unmasked view. Across four benchmarks, LEARN-TS achieves the highest mean performance in 13 of 16 dataset-metric comparisons. Controlled ablations examine observation conditioning, joint normality alignment and scoring, and reference content, showing dataset-dependent ranking benefits and modest average gains from semantic over random references.
发表机构
- Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。
