Dirichlet Process Prior for Student’s t Graph Variational Autoencoders

Yuexuan Zhao and Jing Huang
Additional contact information
Yuexuan Zhao: College of Computer Science and Technology, Jilin University, Changchun 130012, China
Jing Huang: College of Computer Science and Technology, Jilin University, Changchun 130012, China

Future Internet, 2021, vol. 13, issue 3, 1-14

Abstract: Graph variational auto-encoder (GVAE) is a model that combines neural networks and Bayes methods, capable of deeper exploring the influential latent features of graph reconstruction. However, several pieces of research based on GVAE employ a plain prior distribution for latent variables, for instance, standard normal distribution (N(0,1)). Although this kind of simple distribution has the advantage of convenient calculation, it will also make latent variables contain relatively little helpful information. The lack of adequate expression of nodes will inevitably affect the process of generating graphs, which will eventually lead to the discovery of only external relations and the neglect of some complex internal correlations. In this paper, we present a novel prior distribution for GVAE, called Dirichlet process (DP) construction for Student’s t (St) distribution. The DP allows the latent variables to adapt their complexity during learning and then cooperates with heavy-tailed St distribution to approach sufficient node representation. Experimental results show that this method can achieve a relatively better performance against the baselines.

Keywords: neural network; Bayesian nonparametric; Graph variational auto-encoder; Student’s t distribution; Dirichlet process; network representation learning (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/13/3/75/pdf (application/pdf)
https://www.mdpi.com/1999-5903/13/3/75/ (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:gam:jftint:v:13:y:2021:i:3:p:75-:d:517886

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().