An Adaptive Auxiliary Training Method of Autoencoders and Its Application in Anomaly Detection

Li Niu, Jiachun Liao, Feng Sha, Zhaokun Cheng, Yicheng Qiu

Abstract: In various applications of autoencoders, an auxiliary subnetwork is used to improve the performance of a neural network with an autoencoder as the key component. For the specific task of anomaly detection, we have observed that in certain cases, when the reconstruction performance reaches a high level, the auxiliary subnetwork becomes ineffective in further improving the autoencoder’s performance. This phenomenon results in oscillation and degradation of the overall system. To address this issue, we propose an adaptive auxiliary training method (AAT) that ensures continuous improvement in the autoencoder’s reconstruction performance throughout the entire training procedure. AAT enhances the monitoring of the autoencoder’s training, enabling adaptive adjustment of the training strategy without a validation set. Additionally, an anomaly detection scheme is devised based on the proposed adaptive auxiliary training method. Experimental results on multiple datasets prove that the proposed methods produce autoencoders with better reconstruction and detection performances comparing to the state-of-the-art (SOTA) methods.