Drop-in density-aware partitioning for tree-based anomaly detection

Unsupervised isolation tree-based anomaly detection methods are widely used for their simplicity, scalability, and strong empirical performance. However, the standard partition rule, whether drawing thresholds uniformly from feature ranges or sampling random normal vectors for oblique hyperplanes, i...

Descripció completa

Dades bibliogràfiques

Autors principals:	Sijin Yeom, Jae-Hun Jung
Format:	Artigo
Idioma:	Inglês
Publicat:	IOP Publishing 2026-01-01
Col·lecció:	Machine Learning: Science and Technology
Matèries:	unsupervised anomaly detection isolation forest density-aware partitioning density-aware split density-aware direction
Accés en línia:	https://doi.org/10.1088/2632-2153/ae5390
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!