用于可解释多变量时间序列异常检测的结构化时间因果性
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
AI总结：
针对无标签多变量时间序列异常检测中复杂模型不可解释且性能虚高的问题，提出无监督 OracleAD，利用时间因果嵌入、自注意力与 SLS 双重评分实现检测及根因定位。
摘要：
现实世界中的多变量时间序列异常十分罕见，且通常没有标签。此外，主流方法依赖针对基准进行调优的日益复杂的架构，只能检测到异常片段的碎片，并夸大性能。本文提出 OracleAD，这是一个简单且可解释的无监督多变量时间序列异常检测框架。OracleAD 将每个变量的过去序列编码为单个因果嵌入，以联合预测当前时间点并重建输入窗口，从而有效建模时间动态。随后，这些嵌入经过自注意力机制，被投影到共享潜空间并捕获空间关系。这些关系并非静态，因为它们由从每个变量的时间动态中涌现的属性建模。投影后的嵌入与表示正常状态关系的稳定潜结构（Stable Latent Structure，SLS）对齐。异常通过基于预测误差和相对 SLS 偏差的双重评分机制识别，从而能够在每个时间点以及各个变量上进行细粒度异常诊断。由于任何明显的 SLS 偏差都源于违背所学正常数据时间因果性的嵌入，OracleAD 可在嵌入层面直接定位根因变量。OracleAD 在多个真实世界数据集和评估协议上取得了最先进结果，同时通过 SLS 保持可解释性。
英文摘要：
Real-world multivariate time series anomalies are rare and often unlabeled. Additionally, prevailing methods rely on increasingly complex architectures tuned to benchmarks, detecting only fragments of anomalous segments and overstating performance. In this paper, we introduce OracleAD, a simple and interpretable unsupervised framework for multivariate time series anomaly detection. OracleAD encodes each variable's past sequence into a single causal embedding to jointly predict the present time point and reconstruct the input window, effectively modeling temporal dynamics. These embeddings then undergo a self-attention mechanism to project them into a shared latent space and capture spatial relationships. These relationships are not static, since they are modeled by a property that emerges from each variable's temporal dynamics. The projected embeddings are aligned to a Stable Latent Structure (SLS) representing normal-state relationships. Anomalies are identified using a dual scoring mechanism based on prediction error and deviation from the SLS, enabling fine-grained anomaly diagnosis at each time point and across individual variables. Since any noticeable SLS deviation originates from embeddings that violate the learned temporal causality of normal data, OracleAD directly pinpoints the root-cause variables at the embedding level. OracleAD achieves state-of-the-art results across multiple real-world datasets and evaluation protocols, while remaining interpretable through SLS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
