Anomaly Detection by Recombining Gated Unsupervised Experts

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.

arXiv commentAccepted at IJCNN 2022

References in corpus (15)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Learning for Anomaly Detection: A Review
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Deep Learning for Anomaly Detection: A Survey
• A Unifying Review of Deep and Shallow Anomaly Detection
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Self-Normalizing Neural Networks
• Adversarial Autoencoders
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection
• Anomaly Detection using Autoencoders in High Performance Computing Systems
• DAE : Discriminatory Auto-Encoder for multivariate time-series anomaly detection in air transportation
• Deep Weakly-supervised Anomaly Detection
• ${\text{A}}^3$: Activation Anomaly Analysis
• Anomalous Example Detection in Deep Learning: A Survey