Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction

Abstract

Detecting anomalies for multivariate time-series without manual supervision continues a challenging problem due to the increased scale of dimensions and complexity of today's IT monitoring systems. Recent progress of unsupervised time-series anomaly detection mainly use deep autoencoders to solve this problem, i.e. training on normal samples and producing significant reconstruction error on abnormal inputs. However, in practice, autoencoders can reconstruct anomalies so well, due to powerful capabilites of neural networks. Besides, these approaches can be ineffective for identifying non-point anomalies, e.g. contextual anomalies and collective anomalies, since they solely utilze a pointwise reconstruction objective. To tackle the above issues, we propose MemAAE (Memory-augmented Adversarial Autoencoders with Deep Reconstruction and Prediction), a novel unsupervised anomaly detection method for time-series. By jointly training two complementary proxy tasks, reconstruction and prediction, with a shared network architecture, we show that detecting anomalies via multiple tasks obtains superior performance rather than single-task training. Additionally, a compressive memory module is introduced to preserve normal patterns, avoiding unexpected generalization on abnormal inputs. Through extensive experiments, MemAAE achieves an overall F1 score of 0.90 on four public datasets, significantly outperforming the best baseline by 0.02.

Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training

“…Skip-GANomaly [45] introduced a skip-connection to GANomaly to improve the reconstruction quality of the image background. Xiao et al [46] proposed a memoryaugmented adversarial autoencoder (MemAAE) that utilizes a memory mechanism to manipulate latent features. Despite their success in detecting and localizing diverse defects, these GAN-based methods struggle with balancing a noise-free normal background reconstruction and accurate defect localization.…”