DCSO: Dynamic Combination of Detector Scores for Outlier Ensembles

11/23/2019
by   Yue Zhao, et al.
10

Selecting and combining the outlier scores of different base detectors used within outlier ensembles can be quite challenging in the absence of ground truth. In this paper, an unsupervised outlier detector combination framework called DCSO is proposed, demonstrated and assessed for the dynamic selection of most competent base detectors, with an emphasis on data locality. The proposed DCSO framework first defines the local region of a test instance by its k nearest neighbors and then identifies the top-performing base detectors within the local region. Experimental results on ten benchmark datasets demonstrate that DCSO provides consistent performance improvement over existing static combination approaches in mining outlying objects. To facilitate interpretability and reliability of the proposed method, DCSO is analyzed using both theoretical frameworks and visualization techniques, and presented alongside empirical parameter setting instructions that can be used to improve the overall performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/04/2018

LSCP: Locally Selective Combination in Parallel Outlier Ensembles

In unsupervised outlier ensembles, the absence of ground truth makes the...
research
03/17/2023

Neighborhood Averaging for Improving Outlier Detectors

We hypothesize that similar objects should have similar outlier scores. ...
research
08/01/2021

IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation

Outlier detection is one of the most popular and continuously rising top...
research
09/18/2016

Sequential Ensemble Learning for Outlier Detection: A Bias-Variance Perspective

Ensemble methods for classification and clustering have been effectively...
research
01/18/2022

An Efficient Hashing-based Ensemble Method for Collaborative Outlier Detection

In collaborative outlier detection, multiple participants exchange their...
research
04/17/2018

Graph-based Selective Outlier Ensembles

An ensemble technique is characterized by the mechanism that generates t...
research
07/24/2023

Towards Generalizable Deepfake Detection by Primary Region Regularization

The existing deepfake detection methods have reached a bottleneck in gen...

Please sign up or login with your details

Forgot password? Click here to reset