Inlier-Based Outlier Detection via Direct Density Ratio Estimation

Authors:
Shohei Hido;Yuta Tsuboi;Hisashi Kashima;Masashi Sugiyama;Takafumi Kanamori
Affiliations:
-;-;-;-;-
Venue:
ICDM '08 Proceedings of the 2008 Eighth IEEE International Conference on Data Mining
Year:
2008

Citing 0
Cited 6

Dimensionality reduction for density ratio estimation in high-dimensional spaces

Neural Networks
Density Ratio Estimation: A New Versatile Tool for Machine Learning

ACML '09 Proceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning
A Least-squares Approach to Direct Importance Estimation

The Journal of Machine Learning Research
Enhancing effectiveness of density-based outlier mining scheme with density-similarity-neighbor-based outlier factor

Expert Systems with Applications: An International Journal
Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search

Neural Networks
Computational complexity of kernel-based density-ratio estimation: a condition number analysis

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new statistical approach to the problem of inlier-based outlier detection, i.e.,finding outliers in the test set based on the training set consisting only of inliers. Our key idea is to use the ratio of training and test data densities as an outlier score; we estimate the ratio directly in a semi-parametric fashion without going through density estimation. Thus our approach is expected to have better performance in high-dimensional problems. Furthermore, the applied algorithm for density ratio estimation is equipped with a natural cross-validation procedure, allowing us to objectively optimize the value of tuning parameters such as the regularization parameter and the kernel width. The algorithm offers a closed-form solution as well as a closed-form formula for the leave-one-out error. Thanks to this, the proposed outlier detection me thod is computationally very efficient and is scalable to massive datasets. Simulations with benchmark and real-world datasets illustrate the usefulness of the proposed approach.