Generative Adversarial Active Learning for Unsupervised Outlier Detection

Outlier detection is an important topic in machine learning and has been used in a wide range of applications. In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution. However, due to the sparsity of data in h...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering Vol. 32; no. 8; pp. 1517 - 1528
Main Authors: Liu, Yezheng, Li, Zhe, Zhou, Chong, Jiang, Yuanchun, Sun, Jianshan, Wang, Meng, He, Xiangnan
Format: Journal Article
Language:English
Published: New York IEEE 01.08.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Active learning
Anomaly detection
Computational modeling
curse of dimensionality
Data analysis
Data models
Datasets
Gallium nitride
generate potential outliers
generative adversarial active learning
Generative adversarial networks
Generators
Machine learning
mode collapsing problem
multiple-objective generative adversarial active learning
Outlier detection
Outliers (statistics)
Training
ISSN:1041-4347, 1558-2191
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Outlier detection is an important topic in machine learning and has been used in a wide range of applications. In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution. However, due to the sparsity of data in high-dimensional space, a limited number of potential outliers may fail to provide sufficient information to assist the classifier in describing a boundary that can separate outliers from normal data effectively. To address this, we propose a novel Single-Objective Generative Adversarial Active Learning (SO-GAAL) method for outlier detection, which can directly generate informative potential outliers based on the mini-max game between a generator and a discriminator. Moreover, to prevent the generator from falling into the mode collapsing problem, the stop node of training should be determined when SO-GAAL is able to provide sufficient information. But without any prior information, it is extremely difficult for SO-GAAL. Therefore, we expand the network structure of SO-GAAL from a single generator to multiple generators with different objectives (MO-GAAL), which can generate a reasonable reference distribution for the whole dataset. We empirically compare the proposed approach with several state-of-the-art outlier detection methods on both synthetic and real-world datasets. The results show that MO-GAAL outperforms its competitors in the majority of cases, especially for datasets with various cluster types or high irrelevant variable ratio. The experiment codes are available at: https://github.com/leibinghe/GAAL-based-outlier-detection .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2019.2905606