利用对比学习和神经变换进行时间序列异常检测
Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection
AI总结：
提出CNT框架，结合窗口对比学习与可学习变换，解决时间序列异常检测中的表示坍缩问题，并在真实工业数据集上超越多种基线。
摘要：
时间序列异常检测（TSAD）在众多工业应用中扮演着至关重要的角色。尽管对比学习因其从无标签数据中提取有意义表示的能力而在时间序列领域获得了发展势头，但其直接应用于异常检测并非没有障碍。首先，对比学习通常需要负采样以避免表示坍缩问题，即编码器收敛到常数解。然而，从同一数据集中抽取不相似样本并不适合TSAD，因为训练数据集中的大多数样本都是“正常”的。其次，传统的对比学习侧重于实例判别，这可能会忽略那些在与时间上下文比较时可检测到的异常。在本研究中，我们提出了一种新颖的方法CNT，该方法结合了基于窗口的对比学习策略，并辅以可学习的变换。这种双重配置专注于捕获局部区域的时间异常，同时缓解表示坍缩问题。我们的理论分析验证了CNT在规避常数编码器解方面的有效性。通过在多样化的真实世界工业数据集上进行的大量实验，我们展示了我们的框架在超越各种基线和模型变体方面的优越性。
英文摘要：
Time series anomaly detection (TSAD) plays a vital role in many industrial applications. While contrastive learning has gained momentum in the time series domain for its prowess in extracting meaningful representations from unlabeled data, its straightforward application to anomaly detection is not without hurdles. Firstly, contrastive learning typically requires negative sampling to avoid the representation collapse issue, where the encoder converges to a constant solution. However, drawing from the same dataset for dissimilar samples is ill-suited for TSAD as most samples are ``normal'' in the training dataset. Secondly, conventional contrastive learning focuses on instance discrimination, which may overlook anomalies that are detectable when compared to their temporal context. In this study, we propose a novel approach, CNT, that incorporates a window-based contrastive learning strategy fortified with learnable transformations. This dual configuration focuses on capturing temporal anomalies in local regions while simultaneously mitigating the representation collapse issue. Our theoretical analysis validates the effectiveness of CNT in circumventing constant encoder solutions. Through extensive experiments on diverse real-world industrial datasets, we show the superiority of our framework by outperforming various baselines and model variants.
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。
