Graphon Estimation from Partially Observed Network Data
Machine Learning
2019-06-28 v2 Machine Learning
Methodology
Abstract
We consider estimating the edge-probability matrix of a network generated from a graphon model when the full network is not observed---only some overlapping subgraphs are. We extend the neighbourhood smoothing (NBS) algorithm of Zhang et al. (2017) to this missing-data set-up and show experimentally that, for a wide range of graphons, the extended NBS algorithm achieves significantly smaller error rates than standard graphon estimation algorithms such as vanilla neighbourhood smoothing (NBS), universal singular value thresholding (USVT), blockmodel approximation, matrix completion, etc. We also show that the extended NBS algorithm is much more robust to missing data.
Cite
@article{arxiv.1906.00494,
title = {Graphon Estimation from Partially Observed Network Data},
author = {Soumendu Sundar Mukherjee and Sayak Chakrabarti},
journal= {arXiv preprint arXiv:1906.00494},
year = {2019}
}
Comments
12 pages, 7 figures, 1 table