Unsupervised Anomaly Detection by Robust Collaborative Autoencoders

Boyang Liu, Ding Wang, Kaixiang Lin, Pang-Ning Tan, Jiayu Zhou

Keywords: Anomaly Detection, Robustness

Abstract: Unsupervised anomaly detection plays a crucial role in many critical applications. Driven by the success of deep learning, recent years have witnessed growing interests in applying deep neural networks (DNNs) to anomaly detection problems. A common approach is to use autoencoders to learn a feature representation for the normal (non-anomalous) observations in the data. The reconstruction error of the autoencoder is then used as outlier scores to detect anomalies. However, due to the high complexity brought upon by over-parameterization of DNNs, the reconstruction error of the anomalies could also be small, which hampers the effectiveness of these methods. To alleviate this problem, we propose a robust framework using collaborative autoencoders to jointly identify normal observations from the data while learning its feature representation. We investigate the theoretical properties of the framework and empirically show its outstanding performance as compared to other DNN-based methods. Our experimental results also show the resiliency of the framework to missing values compared to other baseline methods.

One-sentence Summary: Unsupervised anomaly detection algorithm which can handle training data corruptions.

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

Reviewed Version (pdf): https://openreview.net/references/pdf?id=3g1WXPYO1C