English

Dimensionality-Aware Outlier Detection: Theoretical and Experimental Analysis

Machine Learning 2024-04-23 v2 Artificial Intelligence

Abstract

We present a nonparametric method for outlier detection that takes full account of local variations in intrinsic dimensionality within the dataset. Using the theory of Local Intrinsic Dimensionality (LID), our 'dimensionality-aware' outlier detection method, DAO, is derived as an estimator of an asymptotic local expected density ratio involving the query point and a close neighbor drawn at random. The dimensionality-aware behavior of DAO is due to its use of local estimation of LID values in a theoretically-justified way. Through comprehensive experimentation on more than 800 synthetic and real datasets, we show that DAO significantly outperforms three popular and important benchmark outlier detection methods: Local Outlier Factor (LOF), Simplified LOF, and kNN.

Keywords

Cite

@article{arxiv.2401.05453,
  title  = {Dimensionality-Aware Outlier Detection: Theoretical and Experimental Analysis},
  author = {Alastair Anderberg and James Bailey and Ricardo J. G. B. Campello and Michael E. Houle and Henrique O. Marques and Miloš Radovanović and Arthur Zimek},
  journal= {arXiv preprint arXiv:2401.05453},
  year   = {2024}
}

Comments

13 pages, 3 figures. Extended version of a paper accepted for publication at the SIAM International Conference on Data Mining (SDM24)

R2 v1 2026-06-28T14:13:37.742Z