Anomaly Detection With Partitioning Overfitting Autoencoder Ensembles
This method addresses the challenge of tuning regularization in autoencoder-based anomaly detection, offering a practical solution for researchers and practitioners, though it is incremental as it builds on existing autoencoder techniques.
The paper tackles the problem of improving unsupervised outlier detection accuracy and reducing regularization tuning burden by proposing POTATOES, which partitions data, overfits autoencoders on each part, and uses maximum reconstruction error as the anomaly score, showing significant performance improvements on realistic datasets when inliers are dense.
In this paper, we propose POTATOES (Partitioning OverfiTting AuTOencoder EnSemble), a new method for unsupervised outlier detection (UOD). More precisely, given any autoencoder for UOD, this technique can be used to improve its accuracy while at the same time removing the burden of tuning its regularization. The idea is to not regularize at all, but to rather randomly partition the data into sufficiently many equally sized parts, overfit each part with its own autoencoder, and to use the maximum over all autoencoder reconstruction errors as the anomaly score. We apply our model to various realistic datasets and show that if the set of inliers is dense enough, our method indeed improves the UOD performance of a given autoencoder significantly. For reproducibility, the code is made available on github so the reader can recreate the results in this paper as well as apply the method to other autoencoders and datasets.