Chandna, Swati and Olhede, S. and Wolfe, P. (2022) Local linear graphon estimation using covariates. Biometrika 109 (3), pp. 721-734. ISSN 1464-3510.
|
Text
47271a.pdf - Published Version of Record Available under License Creative Commons Attribution. Download (534kB) | Preview |
Abstract
We consider local linear estimation of the graphon function which determines probabilities of pairwise edges between nodes within an unlabeled network. Real world networks are typically characterized by node heterogeneity with different nodes exhibiting different degrees of interaction. Existing approaches to graphon estimation are limited to local constant approximations, and are not designed to estimate heterogeneity across the full network. In this paper, we show how continuous node covariates can be employed to estimate heterogeneity in the network via a local linear graphon estimator. We derive the bias and variance of an oracle based local linear graphon estimator and thus obtain the mean integrated squared error optimal bandwidth rule. We also provide a plug-in bandwidth selection procedure, making local linear estimation for unlabeled networks practically feasible. Finite sample performance is investigated in a simulation study. We apply our method to a school friendship network and an email network to illustrate the advantages offered by our approach over existing methods.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | Exchangeable network, Graph limit, Graphon estimation, Nonparametric regression |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Depositing User: | Swati Chandna |
| Date Deposited: | 17 Jan 2022 07:53 |
| Last Modified: | 09 Aug 2023 12:52 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/47271 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
