RIFT: Relative Isolation From Trees For Anomaly Detection
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.
Key points
- 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.
- 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.
Sources (1)
- [1]RIFT: Relative Isolation From Trees For Anomaly DetectionarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 04:22 PM
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.
Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection.
Extractive summary: sentences quoted from the sources.