论文标题
通过分配过度适合自动编码器的异常检测
Anomaly Detection With Partitioning Overfitting Autoencoder Ensembles
论文作者
论文摘要
在本文中，我们提出了土豆（分区过度适合自动编码器集合），这是一种无监督的离群检测（UOD）的新方法。更确切地说，鉴于UOD的任何自动编码器，该技术可用于提高其准确性，同时消除调整正则化的负担。这个想法是完全不正规化，而是将数据随机分配到足够大小的零件中，用自己的自动编码器过度拟合每个零件，并在所有自动编码器重建错误上使用最大值作为异常得分。我们将模型应用于各种现实的数据集，并表明，如果一组嵌入器足够密集，我们的方法确实可以显着提高给定自动编码器的UOD性能。为了可重复性，该代码可在GitHub上提供，以便读者可以在本文中重新创建结果，并将方法应用于其他自动编码器和数据集。
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.
