CRAFTIIF：用于多元时间序列异常检测的跨分辨率分析四类型可解释孤立森林
CRAFTIIF: Cross-Resolution Analytic Four-Type Interpretable Isolation Forest for Multivariate Time Series Anomaly Detection
AI总结：
提出CRAFTIIF无监督框架，通过四种小波特征和五个孤立森林同时检测点、分布、时间和集体四类异常，在mTSBench基准上达到平均F1=0.228，VUS-PR比先前最佳提升40.7%。
摘要：
多元时间序列中的异常检测面临四种结构不同的异常类型——点异常（孤立尖峰）、分布异常（水平偏移）、时间异常（节奏变化）和集体异常（传感器间相关性崩溃）——每种都需要不同的特征表示。大多数无监督方法只针对其中一两种类型，且可解释性有限。我们提出CRAFTIIF（跨分辨率分析四类型可解释孤立森林），这是一个完全无监督的框架，针对所有四种类型，无需针对数据集调整。CRAFTIIF生成K=500个随机分析小波特征，跨越四个小波族（Morlet、DOG、Haar、Coiflet），每个针对特定异常类型，并输入五个结构化的孤立森林——每种类型一个，外加一个用于复合异常的元IF。自适应Otsu/MAD阈值在0.1%到69.2%的异常率范围内自动校准检测。由于每个IF仅针对特定类型的特征进行训练，分支触发直接提供异常类型归因，无需事后解释。在mTSBench基准（Zhou等人，TMLR 2026）的所有19个数据集上评估，CRAFTIIF在全部19个数据集上达到平均F1=0.228，在13个可检测数据集上F1=0.322，在VUS-PR上排名第一（0.463对比之前最佳0.329，提升40.7%）。一个诊断框架——oracle F1、可检测性限制和分支分离比——识别出19个数据集中有6个从根本上无法被任何无监督方法检测。在11种消融条件下，自适应阈值（+38% F1）、四分支结构（+20%）和元IF（+23%）均被证明是必不可少的。代码：此 https URL
英文摘要：
Anomaly detection in multivariate time series is challenged by four structurally distinct anomaly types -- point (isolated spikes), distributional (level shifts), temporal (rhythm changes), and collective (inter-sensor correlation breakdowns) -- each requiring different feature representations. Most unsupervised methods target only one or two types and provide limited interpretability. We present CRAFTIIF (Cross-Resolution Analytic Four-Type Interpretable Isolation Forest), a fully unsupervised framework targeting all four types without dataset-specific tuning. CRAFTIIF generates K=500 random analytic wavelet feature draws across four families (Morlet, DOG, Haar, Coiflet), each targeting a specific anomaly type, feeding five structured Isolation Forests -- one per type plus a meta-IF for compound anomalies. An adaptive Otsu/MAD threshold calibrates detection automatically across anomaly rates from 0.1% to 69.2%. Because each IF is trained exclusively on type-specific features, branch firing provides direct anomaly-type attribution by construction, without post-hoc explanation. Evaluated on all 19 datasets of the mTSBench benchmark (Zhou et al., TMLR 2026), CRAFTIIF achieves mean F1=0.228 (all 19 datasets) and F1=0.322 (13 detectable datasets), ranking first among all 25 evaluated methods on VUS-PR (0.463 vs. previous best 0.329, +40.7%). A diagnostic framework -- oracle F1, detectability limits, and branch separation ratios -- identifies 6 of 19 datasets as fundamentally undetectable by any unsupervised method. Ablation over 11 conditions confirms adaptive thresholding (+38% F1), four-branch structure (+20%), and meta-IF (+23%) are each essential. Code: https://github.com/smitswil/craftiif
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。
