Deep generative replay for multivariate time-series monitoring with variational autoencoders.

Abstract

Multivariate time-series (MTS) play a crucial role in network monitoring and analysis problems. We explore the usage of generative AI for MTS data modeling, in particular for the sake of knowledge replay. Knowledge replay mechanisms help in leveraging past experiences to enhance learning, mitigate forgetting, promote generalization, and enable the transfer of knowledge across different tasks or domains. Using a VAE-based deep architecture for data modeling, we incorporate a Deep Generative Replay (DGR) approach to transfer previously learned latent representations into future learning tasks, enabling continual learning in MTS problems. We study the generative characteristics of VAE-based models on top of a multi-dimensional network monitoring dataset collected from an operational mobile Internet Service Provider (ISP), portraying its usage in the context of DGR learning tasks.