# Preference Isolation Forest for Structure-based Anomaly Detection

arXiv: https://arxiv.org/abs/2505.10876 · HTML: https://mlsanity.com/paper/2505.10876/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [Extended Isolation Forest](https://mlsanity.com/paper/1811.02141/) (2018)
- [Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2207.12201/) (2022)
- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection](https://mlsanity.com/paper/2410.00320/) (2024)
- [Functional Isolation Forest](https://mlsanity.com/paper/1904.04573/) (2019)
- [Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework](https://mlsanity.com/paper/2409.13162/) (2024)
- [PIF: Anomaly detection via preference embedding](https://mlsanity.com/paper/2505.10441/) (2025)

## Abstract (arXiv)

We address the problem of detecting anomalies as samples that do not conform to structured patterns represented by low-dimensional manifolds. To this end, we conceive a general anomaly detection framework called Preference Isolation Forest (PIF), that combines the benefits of adaptive isolation-based methods with the flexibility of preference embedding. The key intuition is to embed the data into a high-dimensional preference space by fitting low-dimensional manifolds, and to identify anomalies as isolated points. We propose three isolation approaches to identify anomalies: i) Voronoi-iForest, the most general solution, ii) RuzHash-iForest, that avoids explicit computation of distances via Local Sensitive Hashing, and iii) Sliding-PIF, that leverages a locality prior to improve efficiency and effectiveness.