Distribution and volume based scoring for Isolation Forests

TL;DR

This paper enhances the Isolation Forest algorithm for anomaly detection by introducing a distribution-aware scoring method and a hyper-volume based scoring at the tree level, leading to improved detection performance.

Contribution

It proposes a novel information-theoretic generalization of the score function and an alternative hyper-volume based scoring method for Isolation Forests.

Findings

Significant improvement over standard Isolation Forest on some datasets.

Average performance boost across all datasets for one proposed variant.

Code is publicly available for reproducibility.

Abstract

We make two contributions to the Isolation Forest method for anomaly and outlier detection. The first contribution is an information-theoretically motivated generalisation of the score function that is used to aggregate the scores across random tree estimators. This generalisation allows one to take into account not just the ensemble average across trees but instead the whole distribution. The second contribution is an alternative scoring function at the level of the individual tree estimator, in which we replace the depth-based scoring of the Isolation Forest with one based on hyper-volumes associated to an isolation tree's leaf nodes. We motivate the use of both of these methods on generated data and also evaluate them on 34 datasets from the recent and exhaustive ``ADBench'' benchmark, finding significant improvement over the standard isolation forest for both variants on some datasets and improvement on average across all datasets for one of the two variants. The code to reproduce our results is made available as part of the submission.