Isolation-based Spherical Ensemble Representations for Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Yang, Yang, Sikun, Tian, Hao, He, Kai, Qi, Lianyong, Liu, Ming, Yang, Yujiu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914094087405568
author Cao, Yang
Yang, Sikun
Tian, Hao
He, Kai
Qi, Lianyong
Liu, Ming
Yang, Yujiu
author_facet Cao, Yang
Yang, Sikun
Tian, Hao
He, Kai
Qi, Lianyong
Liu, Ming
Yang, Yujiu
contents Anomaly detection is a critical task in data mining and management with applications spanning fraud detection, network security, and log monitoring. Despite extensive research, existing unsupervised anomaly detection methods still face fundamental challenges including conflicting distributional assumptions, computational inefficiency, and difficulty handling different anomaly types. To address these problems, we propose ISER (Isolation-based Spherical Ensemble Representations) that extends existing isolation-based methods by using hypersphere radii as proxies for local density characteristics while maintaining linear time and constant space complexity. ISER constructs ensemble representations where hypersphere radii encode density information: smaller radii indicate dense regions while larger radii correspond to sparse areas. We introduce a novel similarity-based scoring method that measures pattern consistency by comparing ensemble representations against a theoretical anomaly reference pattern. Additionally, we enhance the performance of Isolation Forest by using ISER and adapting the scoring function to address axis-parallel bias and local anomaly detection limitations. Comprehensive experiments on 22 real-world datasets demonstrate ISER's superior performance over 11 baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Isolation-based Spherical Ensemble Representations for Anomaly Detection
Cao, Yang
Yang, Sikun
Tian, Hao
He, Kai
Qi, Lianyong
Liu, Ming
Yang, Yujiu
Machine Learning
Anomaly detection is a critical task in data mining and management with applications spanning fraud detection, network security, and log monitoring. Despite extensive research, existing unsupervised anomaly detection methods still face fundamental challenges including conflicting distributional assumptions, computational inefficiency, and difficulty handling different anomaly types. To address these problems, we propose ISER (Isolation-based Spherical Ensemble Representations) that extends existing isolation-based methods by using hypersphere radii as proxies for local density characteristics while maintaining linear time and constant space complexity. ISER constructs ensemble representations where hypersphere radii encode density information: smaller radii indicate dense regions while larger radii correspond to sparse areas. We introduce a novel similarity-based scoring method that measures pattern consistency by comparing ensemble representations against a theoretical anomaly reference pattern. Additionally, we enhance the performance of Isolation Forest by using ISER and adapting the scoring function to address axis-parallel bias and local anomaly detection limitations. Comprehensive experiments on 22 real-world datasets demonstrate ISER's superior performance over 11 baseline methods.
title Isolation-based Spherical Ensemble Representations for Anomaly Detection
topic Machine Learning
url https://arxiv.org/abs/2510.13311