arXiv 2504.142042025-05-02cs.LGcs.AI

DConAD：一种用于时间序列异常检测的基于差分的对比表示学习框架

DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection

University of Chinese Academy of Science（中国科学院大学）；Tsinghua University（清华大学）；Shanghai University of International Business and Economics（上海国际商务经济学院）；Northeast Normal University（东北师范大学）；Fuzhou University（福州市大学）；Hubei University（湖北大学）；Hainan University（海南大学）；Northeastern University（东北大学）

Wenxin Zhang, Xiaojian Lin, Wenjun Yu, Guangzhen Yao, jingxiang Zhong, Yu Li, Renda Han, Songcheng Xu, Hao Shi, Cuicui Luo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对时间序列异常检测中异常模式多样与数据复杂等问题，提出基于差分的对比表示学习框架DConAD，利用差分数据与transformer捕获时空依赖，并结合基于KL散度的正样本对比学习与停止梯度策略，在五个数据集上优于九个基线。

摘要：

时间序列异常检测对于各种应用领域中的风险识别和故障检测具有重要意义。无监督学习方法因其不需要标签而变得流行。然而，由于异常模式的多样性、异常的稀疏性以及数据规模和复杂性的增长带来的挑战，这些方法往往无法捕获时间序列内稳健且具有代表性的依赖关系来识别异常。为了增强模型捕获时间序列正常模式的能力，并避免因依赖高质量先验知识而导致的建模能力退化，我们提出了一种用于时间序列异常检测的基于差分的对比表示学习框架（DConAD）。具体而言，DConAD生成差分数据以提供关于时间序列的额外信息，并利用基于transformer的架构来捕获时空依赖关系，从而增强了无偏表示学习能力的稳健性。此外，DConAD实现了一种新颖的基于KL散度的对比学习范式，该范式仅使用正样本以避免偏离重构，并部署停止梯度策略以促使收敛。在五个公共数据集上的大量实验表明，与九个基线相比，DConAD具有优越性和有效性。代码可在https://github.com/shaieesss/DConAD获取。

英文摘要：

Time series anomaly detection holds notable importance for risk identification and fault detection across diverse application domains. Unsupervised learning methods have become popular because they have no requirement for labels. However, due to the challenges posed by the multiplicity of abnormal patterns, the sparsity of anomalies, and the growth of data scale and complexity, these methods often fail to capture robust and representative dependencies within the time series for identifying anomalies. To enhance the ability of models to capture normal patterns of time series and avoid the retrogression of modeling ability triggered by the dependencies on high-quality prior knowledge, we propose a differencing-based contrastive representation learning framework for time series anomaly detection (DConAD). Specifically, DConAD generates differential data to provide additional information about time series and utilizes transformer-based architecture to capture spatiotemporal dependencies, which enhances the robustness of unbiased representation learning ability. Furthermore, DConAD implements a novel KL divergence-based contrastive learning paradigm that only uses positive samples to avoid deviation from reconstruction and deploys the stop-gradient strategy to compel convergence. Extensive experiments on five public datasets show the superiority and effectiveness of DConAD compared with nine baselines. The code is available at https://github.com/shaieesss/DConAD.

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。