CANDI：为分布偏移下的多变量时间序列异常检测设计的精选测试时适应
CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift
AI总结：
CANDI提出了一种新的测试时适应框架，通过精选潜在的假阳性样本并保留预训练知识，提升多变量时间序列异常检测在分布偏移下的性能，实验显示其在AUROC上提升达14%。
摘要：
多变量时间序列异常检测（MTSAD）旨在识别多变量时间序列中的异常偏离，对实际应用至关重要。然而，在现实部署中，分布偏移普遍存在，导致预训练异常检测器性能下降。测试时适应（TTA）通过仅使用未标记测试数据实时更新预训练模型，成为解决此挑战的有力方法。本文提出CANDI（Curated test-time adaptation for multivariate time-series ANomaly detection under DIstribution shift），一种新的TTA框架，通过选择性识别和适应潜在假阳性样本，同时保留预训练知识。CANDI引入了假阳性挖掘（FPM）策略，基于异常分数和潜在相似性精选适应样本，并结合可插拔的时空感知正常性适应（SANA）模块进行结构化模型更新。大量实验表明，CANDI在分布偏移下显著提升了MTSAD性能，使AUROC提升高达14%，同时使用更少的适应样本。
英文摘要：
Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and cause severe performance degradation in pre-trained anomaly detector. Test-time adaptation (TTA) updates a pre-trained model on-the-fly using only unlabeled test data, making it promising for addressing this challenge. In this study, we propose CANDI (Curated test-time adaptation for multivariate time-series ANomaly detection under DIstribution shift), a novel TTA framework that selectively identifies and adapts to potential false positives while preserving pre-trained knowledge. CANDI introduces a False Positive Mining (FPM) strategy to curate adaptation samples based on anomaly scores and latent similarity, and incorporates a plug-and-play Spatiotemporally-Aware Normality Adaptation (SANA) module for structurally informed model updates. Extensive experiments demonstrate that CANDI significantly improves the performance of MTSAD under distribution shift, improving AUROC up to 14% while using fewer adaptation samples.
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。
