DCdetector：用于时间序列异常检测的双注意力对比表示学习
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
AI总结：
提出DCdetector，一种多尺度双注意力对比表示学习模型，通过非对称设计和纯对比损失学习置换不变表示，在多个时间序列异常检测基准上取得最先进结果。
摘要：
时间序列异常检测在广泛的应用中至关重要，其目标是从时间序列的正常样本分布中识别出偏离的样本。该任务最根本的挑战是学习一种能够有效区分异常的表征映射。基于重构的方法仍然占据主导地位，但带有异常的表示学习可能因其较大的异常损失而损害性能。另一方面，对比学习旨在找到一种能够清晰区分任何实例与其他实例的表示，这可以为时间序列异常检测带来更自然且更有前景的表示。在本文中，我们提出了DCdetector，一种多尺度双注意力对比表示学习模型。DCdetector利用新颖的双注意力非对称设计来创建置换环境，并使用纯对比损失来指导学习过程，从而学习到具有卓越判别能力的置换不变表示。大量实验表明，DCdetector在多个时间序列异常检测基准数据集上取得了最先进的结果。代码公开于https://github.com/DAMO-DI-ML/KDD2023-DCdetector。
英文摘要：
Time series anomaly detection is critical for a wide range of applications. It aims to identify deviant samples from the normal sample distribution in time series. The most fundamental challenge for this task is to learn a representation map that enables effective discrimination of anomalies. Reconstruction-based methods still dominate, but the representation learning with anomalies might hurt the performance with its large abnormal loss. On the other hand, contrastive learning aims to find a representation that can clearly distinguish any instance from the others, which can bring a more natural and promising representation for time series anomaly detection. In this paper, we propose DCdetector, a multi-scale dual attention contrastive representation learning model. DCdetector utilizes a novel dual attention asymmetric design to create the permutated environment and pure contrastive loss to guide the learning process, thus learning a permutation invariant representation with superior discrimination abilities. Extensive experiments show that DCdetector achieves state-of-the-art results on multiple time series anomaly detection benchmark datasets. Code is publicly available at https://github.com/DAMO-DI-ML/KDD2023-DCdetector.
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。
