November 2018
·
168 Reads
·
156 Citations
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
November 2018
·
168 Reads
·
156 Citations
August 2018
·
507 Reads
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. In particular, we propose to oversample infrequent normal samples - normal samples that occur with small probability, e.g., rare normal events. We show that these samples are responsible for false positives in anomaly detection. However, oversampling of infrequent normal samples is challenging for real-world high-dimensional data with multimodal distributions. To address this challenge, we propose to use a GAN variant known as the adversarial autoencoder (AAE) to transform the high-dimensional multimodal data distributions into low-dimensional unimodal latent distributions with well-defined tail probability. Then, we systematically oversample at the `edge' of the latent distributions to increase the density of infrequent normal samples. We show that our oversampling pipeline is a unified one: it is generally applicable to datasets with different complex data distributions.
... To date, two types of methods have been introduced to address the data imbalance issue, which are the data augmentation methods and data reconstruction methods. The main purpose of augmentation method is to manually produce a number of abnormal samples according to their data characteristics [31]. Data reconstruction method aims to establish the mapping of potential space to sample space by utilizing a generative model (e.g., Variation AutoEncoder (VAE) [29], generative adversarial network (GAN) [18], and Denoising Diffusion Probabilistic Models (DDPM) [22]). ...
November 2018