针对高值异常检测，提出两种新距离度量方法。
Monotonic anomaly detection
- 引入非对称距离度量：Ramp与Signed距离，捕捉属性值单调性。
- 合成数据上Ramp距离显著优于传统绝对距离。
- 适合关注单向异常（如过高/过低）的场景。
半监督异常检测基于异常样本与正常训练数据的差异性。但在某些场景下，我们特别关注属性值过高（或过低）的异常，而非双向偏离。本文提出两种非对称距离度量——梯形距离（ramp distance）和带符号距离（signed distance），以考虑这种单调性。在合成与真实数据集上的实验表明，梯形距离在异常检测性能上显著优于传统绝对距离；而带符号距离在合成数据上表现良好，但在真实数据集上明显劣化。原因在于：使用带符号距离时，某些属性的低值会自动抵消其他属性的高值，导致异常检测退化为简单统计属性总和，该策略在实际中过于简化。
原文摘要 · Abstract (English)
Semi-supervised anomaly detection is based on the principle that potential anomalies are those records that look different from normal training data. However, in some cases we are specifically interested in anomalies that correspond to high attribute values (or low, but not both). We present two asymmetrical distance measures that take this monotonicity into account: ramp distance and signed distance. Through experiments on synthetic and real-life datasets, we show that ramp distance increases anomaly detection performance over the traditional absolute distance. While signed distance also performs well on synthetic data, it performs substantially poorer on real-life datasets. We argue that this is a consequence of the fact that when using signed distance, low values of certain attributes automatically compensate for high values of other attributes, such that anomaly detection is reduced to counting the total attribute value sum, which is too simplistic in practice.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。