基于分解的多尺度Transformer框架用于时间序列异常检测
Decomposition-based multi-scale transformer framework for time series anomaly detection
AI总结：
提出基于分解的多尺度Transformer框架TransDe，结合时间序列分解与对比学习，以异步损失函数提升多变量时间序列异常检测性能，在五个数据集上优于十二个基线。
摘要：
时间序列异常检测对于维持系统稳定至关重要。现有方法面临两大挑战。首先，直接建模序列中多样且复杂模式的依赖关系较为困难。其次，许多使用均方误差优化参数的方法难以应对时间序列中的噪声，导致性能下降。为解决这些问题，我们提出了一个基于分解的Transformer框架（TransDe），用于多变量时间序列异常检测。其核心思想是结合时间序列分解与Transformer的优势，有效学习正常时间序列数据中的复杂模式。我们提出了一种基于多尺度补丁的Transformer架构，以挖掘时间序列各分解成分的代表性依赖关系。此外，提出了一种基于补丁操作的对比学习范式，利用KL散度对齐正样本对，即不同补丁级别视图之间正常模式的纯净表示。进一步引入了一种带有停止梯度策略的新型异步损失函数，以有效提升TransDe的性能，避免优化过程中耗时且劳动密集的计算成本。我们在五个公开数据集上进行了大量实验，TransDe在F1分数上优于十二个基线方法。我们的代码可在https://github.com/shaieesss/TransDe获取。
英文摘要：
Time series anomaly detection is crucial for maintaining stable systems. Existing methods face two main challenges. First, it is difficult to directly model the dependencies of diverse and complex patterns within the sequences. Second, many methods that optimize parameters using mean squared error struggle with noise in the time series, leading to performance deterioration. To address these challenges, we propose a transformer-based framework built on decomposition (TransDe) for multivariate time series anomaly detection. The key idea is to combine the strengths of time series decomposition and transformers to effectively learn the complex patterns in normal time series data. A multi-scale patch-based transformer architecture is proposed to exploit the representative dependencies of each decomposed component of the time series. Furthermore, a contrastive learn paradigm based on patch operation is proposed, which leverages KL divergence to align the positive pairs, namely the pure representations of normal patterns between different patch-level views. A novel asynchronous loss function with a stop-gradient strategy is further introduced to enhance the performance of TransDe effectively. It can avoid time-consuming and labor-intensive computation costs in the optimization process. Extensive experiments on five public datasets are conducted and TransDe shows superiority compared with twelve baselines in terms of F1 score. Our code is available at https://github.com/shaieesss/TransDe.
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。
