arXiv：cs.LG· Mark Daniel Szalai, Gabor Horvath·· 3 小时前
RIFT：基于树的相对隔离度异常检测方法
RIFT: Relative Isolation From Trees For Anomaly Detection
AI 导读
RIFT（Relative Isolation From Trees）是一种确定性异常检测方法，通过生成最小生成树并以各点视角下树边表观尺寸之和为每个点打分，在一维数据上可精确还原 Isolation Forest 的闭式极限。
正文
Abstract:Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-forest limit for one-dimensional data. Inspired by the geometric interpretation of this formula, we introduce RIFT (Relative Isolation From Trees), a deterministic anomaly detection method that generates the minimum spanning tree and scores each point by the sum of the apparent sizes of tree edges as viewed from that point. For one-dimensional data, the RIFT score recovers the closed-form IF limit exactly. In higher dimensions, it provides a parameter-free generalization that is deterministic, robust to varying density and clustered anomalies and avoids the axis-parallel artifacts of IF. We further propose an ensemble variant for large datasets. Experiments on synthetic data and the ADBench benchmark demonstrate that the accuracy is comparable to IF, while the ensemble variant exhibits significantly lower variance across random seeds.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12244 [cs.LG] |
| (or arXiv:2610.12244v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12244 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gabor Horvath [view email]
[v1]
Thu, 8 Oct 2026 16:22:42 UTC (636 KB)
来源：arXiv：cs.LG · arxiv.org