Paper ID: 2310.06047
Knowledge Distillation for Anomaly Detection
Adrian Alan Pol, Ekaterina Govorkova, Sonja Gronroos, Nadezda Chernyavskaya, Philip Harris, Maurizio Pierini, Isobel Ojalvo, Peter Elmer
Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the deployment on resource-constrained devices. We present a novel procedure based on knowledge distillation for compressing an unsupervised anomaly detection model into a supervised deployable one and we suggest a set of techniques to improve the detection sensitivity. Compressed models perform comparably to their larger counterparts while significantly reducing the size and memory footprint.
Submitted: Oct 9, 2023