DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging training sets. Previous work primarily focused on data augmentation for semi-supervised and supervised tasks. In this p...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE International Conference on Data Mining (ICDM) pp. 1122 - 1127
Main Authors Lim, Swee Kiat, Loo, Yi, Tran, Ngoc-Trung, Cheung, Ngai-Man, Roig, Gemma, Elovici, Yuval
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2018
Subjects
adversarial autoencoders
Anomaly detection
data augmentation
Decoding
Doping
Gallium nitride
Gaussian distribution
generative adversarial networks
Training
unsupervised learning
Online AccessGet full text

Cover

More Information
Summary:Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging training sets. Previous work primarily focused on data augmentation for semi-supervised and supervised tasks. In this paper, we instead focus on unsupervised anomaly detection and propose a novel generative data augmentation framework optimized for this task. By using a GAN variant known as the adversarial autoencoder (AAE), we impose a distribution on the latent space of the dataset and systematically sample the latent space to generate artificial samples. To the best of our knowledge, our method is the first data augmentation technique focused on improving performance in unsupervised anomaly detection. We validate our method by demonstrating consistent improvements across several real-world datasets.
ISSN:2374-8486
DOI:10.1109/ICDM.2018.00146