AD-NEV: A Scalable Multi-level Neuroevolution Framework for Multivariate Anomaly Detection
This work addresses the problem of automated model optimization for anomaly detection in cyberphysical and failure prediction systems, presenting an incremental improvement by integrating multiple optimization levels into a neuroevolution framework.
The authors tackled the cumbersome and time-consuming model optimization process for multivariate anomaly detection by proposing AD-NEV, a scalable multi-level neuroevolution framework that synergically optimizes feature subspaces, model architectures, and network weights; experimental results show it outperforms well-known deep learning architectures on benchmark datasets and is efficient and scalable with multiple GPUs.
Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given dataset is a cumbersome and time consuming process. Neuroevolution could be an effective and efficient solution to this problem, as a fully automated search method for learning optimal neural networks, supporting both gradient and non-gradient fine tuning. However, existing methods mostly focus on optimizing model architectures without taking into account feature subspaces and model weights. In this work, we propose Anomaly Detection Neuroevolution (AD-NEv) - a scalable multi-level optimized neuroevolution framework for multivariate time series anomaly detection. The method represents a novel approach to synergically: i) optimize feature subspaces for an ensemble model based on the bagging technique; ii) optimize the model architecture of single anomaly detection models; iii) perform non-gradient fine-tuning of network weights. An extensive experimental evaluation on widely adopted multivariate anomaly detection benchmark datasets shows that the models extracted by AD-NEv outperform well-known deep learning architectures for anomaly detection. Moreover, results show that AD-NEv can perform the whole process efficiently, presenting high scalability when multiple GPUs are available.