AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
This addresses the problem of detecting anomalies in dynamic, categorical data for domains like cybersecurity and online advertising, though it appears incremental as it builds on existing techniques.
The paper tackled anomaly detection on high-dimensional, time-evolving categorical data without labels by proposing AMAD, which combines adversarial autoencoders and recurrent neural networks with attention mechanisms, achieving superior performance over state-of-the-art methods in experiments on three datasets.
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising. The recent trend in these areas calls for anomaly detection on time-evolving data with high-dimensional categorical features without labeled samples. Also, there is an increasing demand for identifying and monitoring irregular patterns at multiple resolutions. In this work, we propose a unified end-to-end approach to solve these challenges by combining the advantages of Adversarial Autoencoder and Recurrent Neural Network. The model learns data representations cross different scales with attention mechanisms, on which an enhanced two-resolution anomaly detector is developed for both instances and data blocks. Extensive experiments are performed over three types of datasets to demonstrate the efficacy of our method and its superiority over the state-of-art approaches.