CAST：上下文与异常结构条件化的时间序列异常生成
CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation
浏览论文内容
中文总结 AI 辅助
针对异常时间序列稀缺且形态异质的问题，提出CAST框架，通过两阶段预训练与微调，利用正常数据学习动态并条件化异常结构，在多个真实数据集上优于现有方法。
中文摘要 AI 辅助
异常时间序列在安全关键领域发挥着至关重要的作用，然而它们本质上稀缺、异质且获取成本高昂。现有的时间序列生成方法主要侧重于合成正常数据，在需要异常样本时提供的价值有限。我们识别出异常生成中的两个基本挑战：（i）异常数据的稀缺性，以及（ii）异常形态特征的异质性。为应对这些挑战，我们提出了CAST，一种上下文与异常结构条件化的时间序列异常生成框架，并配以原则性的两阶段预训练和微调策略。在预训练阶段，我们利用丰富的正常时间序列数据来学习底层系统动态，从而大幅缓解异常数据可用性有限的问题。在微调阶段，CAST显式地将生成器条件化于学习到的异常结构表示，使其能够在相似上下文条件下捕获异质的异常形态。在多个真实世界单变量和多变量数据集上的大量实验表明，CAST在生成保真度和下游任务效用方面均持续优于最先进的异常生成方法，凸显了所提出方法的有效性。
英文摘要
Anomalous time series play a critical role in safety-critical domains, yet they are inherently scarce, heterogeneous, and costly to obtain. Existing time series generation methods predominantly focus on synthesizing normal data, providing limited value when anomalous samples are needed. We identify two fundamental challenges in anomaly generation: (i) the scarcity of anomaly data, and (ii) the heterogeneous morphological characteristics of anomalies. To address these challenges, we propose CAST, a Context- and Anomaly Structure-conditioned Time series anomaly generation framework with principled two-stage pretraining and finetuning strategy. In pretraining stage, we leverage abundant normal time series data to learn underlying system dynamics and substantially mitigate the limited availability of anomaly data. During finetuning, CAST explicitly conditions the generator on learned anomaly structure representations, enabling it to capture heterogeneous anomaly morphologies under similar contextual conditions. Extensive experiments on multiple real-world univariate and multivariate datasets demonstrate that CAST consistently outperforms state-of-the-art anomaly generation methods in terms of both generation fidelity and downstream task utility, highlighting the effectiveness of the proposed approach.
