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

Clarkson, J., Cucuringu, M., Elliott, A. and Reinert, G. (2022) DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series. In: LOG 2022 Learning on Graphs Conference, 9-12 December 2022,

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.

• Item Type: Conference Proceedings
• Additional Information: J.C. acknowledges funding from the EPSRC CDT in Modern Statistics and Statistical Machine Learning (EP/S023151/1), and The Alan Turing Institute’s Finance and Economics Programme. M.C. acknowledges support from the EPSRC grants EP/N510129/1 and EP/W037211/1 at The Alan Turing Institute. A.E. is supported by The Alan Turing Institute’s Finance and Economics Programme and in part by EPSRC grant EP/W037211/1 at The Alan Turing Institute. G.R. is supported in part by EPSRC grants EP/T018445/1, EP/W037211/1 and EP/R018472/1.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Elliott, Dr Andrew
• Authors: Clarkson, J., Cucuringu, M., Elliott, A., and Reinert, G.
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• Copyright Holders: Copyright © The authors and PMLR 2023
• First Published: First published in Proceedings of the First Learning on Graphs Conference, PMLR 198:23:1-23:19
• Publisher Policy: Reproduced in accordance with the publisher copyright policy