DAMNETS: a deep autoregressive model for generating Markovian network time series

Conference item

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.

Authors: Clarkson, J; Cucuringu, M; Elliott, A; Reinert, G

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Journal of Machine Learning Research
• Host title: Proceedings of the First Learning on Graphs Conference
• Pages: 23:1-23:19
• Article number: 23
• Series: Proceedings of Machine Learning Research
• Series number: 198
• Publication date: 2022-12-12
• Acceptance date: 2022-11-24
• Event title: Learning on Graphs conference (LoG) 2022
• Event location: Online
• Event website: https://logconference.org/
• Event start date: 2022-12-09
• Event end date: 2022-12-12
• ISSN: 2640-3498
• Language: English
• Keywords: FFR; dynamic graph; deep generative model; network time series