Novelty Detection via Robust Variational Autoencoding

Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman

Keywords: novelty detection, variational autoencoding, robustness, Wasserstein metric, one-class classification, semi-supervised anomaly detection

Abstract: We propose a new method for novelty detection that can tolerate high corruption of the training points, whereas previous works assumed either no or very low corruption. Our method trains a robust variational autoencoder (VAE), which aims to generate a model for the uncorrupted training points. To gain robustness to high corruption, we incorporate the following four changes to the common VAE: 1. Extracting crucial features of the latent code by a carefully designed dimension reduction component for distributions; 2. Modeling the latent distribution as a mixture of Gaussian low-rank inliers and full-rank outliers, where the testing only uses the inlier model; 3. Applying the Wasserstein-1 metric for regularization, instead of the Kullback-Leibler (KL) divergence; and 4. Using a least absolute deviation error for reconstruction. We establish both robustness to outliers and suitability to low-rank modeling of the Wasserstein metric as opposed to the KL divergence. We illustrate state-of-the-art results on standard benchmarks for novelty detection.

One-sentence Summary: A novel method for novelty detection which allows high corruption of the training set

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2006.05534/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=q7yGKeFNpA