| Title | Anomaly Detection by Recombining Gated Unsupervised Experts |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Schulze, Jan-Philipp, Sperl, Philip, Böttinger, Konstantin |
| Conference Name | 2022 International Joint Conference on Neural Networks (IJCNN) |
| Date Published | jul |
| Keywords | Analytical models, anomaly detection, data mining, Deep Learning, expert systems, Fuses, Human Behavior, IT Security, Knowledge engineering, Logic gates, mixture-of-experts, Neural networks, pubcrawl, resilience, Resiliency, Scalability, security, Training data, unsupervised learning |
| Abstract | 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. |
| DOI | 10.1109/IJCNN55064.2022.9892807 |
| Citation Key | schulze_anomaly_2022 |
Anomaly Detection by Recombining Gated Unsupervised Experts