# Novelty Detection via Robust Variational Autoencoding

arXiv: https://arxiv.org/abs/2006.05534 · HTML: https://mlsanity.com/paper/2006.05534/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

## Built on by (most cited first, 2 of 2)

- [GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps](https://mlsanity.com/paper/2311.06153/) (2023)
- [Repairing Systematic Outliers by Learning Clean Subspaces in VAEs](https://mlsanity.com/paper/2207.08050/) (2022)

## Abstract (arXiv)

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 robust 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.