Joint sparsity-biased variational graph autoencoders

Lane Lawley, Will Frey, Patrick Mullen and Alexander D Wissner-Gross

The Journal of Defense Modeling and Simulation, 2021, vol. 18, issue 3, 239-246

Abstract: To bring the full benefits of machine learning to defense modeling and simulation, it is essential to first learn useful representations for sparse graphs consisting of both key entities (vertices) and their relationships (edges). Here, we present a new model, the Joint Sparsity-Biased Variational Graph AutoEncoder (JSBVGAE), capable of learning embedded representations of nodes from which both sparse network topologies and node features can be jointly and accurately reconstructed. We show that our model outperforms the previous state of the art on standard link-prediction and node-classification tasks, and achieves significantly higher whole-network reconstruction accuracy, while reducing the number of trained parameters.

Keywords: Machine learning; variational autoencoders; graph neural networks; representation learning (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1548512921996828 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:joudef:v:18:y:2021:i:3:p:239-246

DOI: 10.1177/1548512921996828

Access Statistics for this article

More articles in The Journal of Defense Modeling and Simulation
Bibliographic data for series maintained by SAGE Publications ().