DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series

TL;DR

DAMNETS is a scalable deep autoregressive model that effectively generates realistic network time series, capturing complex temporal and structural dynamics, and outperforms existing methods on various datasets.

Contribution

This paper introduces DAMNETS, a novel deep autoregressive model specifically designed for scalable generation of network time series with complex dependencies.

Findings

DAMNETS outperforms competing models on sample quality measures.

The model is effective on both real and synthetic datasets.

DAMNETS demonstrates scalability and flexibility in dynamic graph generation.

Abstract

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.