CALAD：面向多元时间序列异常检测的信道感知对比学习
CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection
AI总结：
提出CALAD框架，通过估计信道相关性指导对比样本构建，结合对比学习和辅助重构头，实现信道感知的多元时间序列异常检测，在分布漂移场景下优于现有方法。
摘要：
多元时间序列异常检测在实际应用中变得越来越重要，而标记数据往往稀缺。许多现有方法依赖无监督学习来建模正常模式，但它们通常平等对待所有信道。这种设计会稀释异常相关信号，因为并非所有信道对异常检测的贡献相同。在本文中，我们提出CALAD，一种用于多元时间序列异常检测的信道感知对比学习框架。CALAD利用估计的信道相关性指导对比样本的构建，使学习过程反映异常语义而非通用相似性。信道相关性通过基于Transformer的自编码器的重构误差进行估计，并用于区分对异常行为影响更大的信道。利用这些信息，我们设计了一种信道级增强策略，其中正负样本基于异常相关信道是否被保留或扰动来构建。这鼓励对无关信道的变化保持不变性，同时对异常相关信道的变化保持敏感性。此外，CALAD结合了对比学习和辅助重构头，使模型在保留正常结构的同时学习判别性表示。在多个真实数据集上的实验表明，CALAD在分布漂移场景下持续优于现有方法。我们提供可复现的代码：https://github.com/hirundo1218/CALAD。
英文摘要：
Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many existing approaches rely on unsupervised learning to model normal patterns, but they often treat all channels equally. This design can dilute anomaly-relevant signals, since not all channels contribute equally to anomaly detection. In this paper, we propose CALAD, a channel-aware contrastive learning framework for multivariate time series anomaly detection. CALAD governs the construction of contrastive samples using estimated channel relevance, allowing the learning process to reflect anomaly semantics rather than generic similarity. Channel relevance is estimated from reconstruction errors of a transformer-based autoencoder and is used to distinguish channels that are more influential to anomalous behaviors. Using this information, we design a channel-wise augmentation strategy in which positive and negative samples are constructed based on whether anomaly-relevant channels are preserved or perturbed. This encourages invariance to changes in irrelevant channels while being sensitive to changes in anomaly-relevant channels. Furthermore, CALAD combines contrastive learning and an auxiliary reconstruction head, allowing the model to learn discriminative representations while retaining normal structures. Experiments on multiple real-world datasets shows that CALAD consistently outperforms existing methods, particularly under distribution shift scenarios. We provide the code for reproducibility at https://github.com/hirundo1218/CALAD
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。
