DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series
This work addresses the problem of modeling complex graph-based dynamics for researchers in fields like epidemiology, biology, and economics, representing an incremental improvement with a novel method for a known bottleneck.
The authors tackled the challenge of generating network time series, which are high-dimensional and require capturing temporal dependencies and network structure, by introducing DAMNETS, a scalable deep generative model that outperforms competing methods on sample quality measures across real and synthetic datasets.
Generative models for network time series (also known as dynamic graphs) have tremendous potential in fields such as epidemiology, biology and economics, where complex graph-based dynamics are core objects of study. Designing flexible and scalable generative models is a very challenging task due to the high dimensionality of the data, as well as the need to represent temporal dependencies and marginal network structure. Here we introduce DAMNETS, a scalable deep generative model for network time series. DAMNETS outperforms competing methods on all of our measures of sample quality, over both real and synthetic data sets.