Anomaly Detection by Recombining Gated Unsupervised Experts
This is an incremental improvement for anomaly detection tasks in machine learning.
The paper tackles anomaly detection by introducing ARGUE, a method that combines expert networks in unsupervised, semi-supervised, and self-supervised settings, showing that prior knowledge of normal data can be as valuable as known anomalies.
Anomaly detection has been considered under several extents of prior knowledge. Unsupervised methods do not require any labelled data, whereas semi-supervised methods leverage some known anomalies. Inspired by mixture-of-experts models and the analysis of the hidden activations of neural networks, we introduce a novel data-driven anomaly detection method called ARGUE. Our method is not only applicable to unsupervised and semi-supervised environments, but also profits from prior knowledge of self-supervised settings. We designed ARGUE as a combination of dedicated expert networks, which specialise on parts of the input data. For its final decision, ARGUE fuses the distributed knowledge across the expert systems using a gated mixture-of-experts architecture. Our evaluation motivates that prior knowledge about the normal data distribution may be as valuable as known anomalies.