Low-dimensional statistical manifold embedding of directed graphs
Machine Learning
2020-02-07 v3 Machine Learning
Abstract
We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way. Each node is encoded with a probability density function over a measurable space. Furthermore, we analyze the connection between the geometrical properties of such embedding and their efficient learning procedure. Extensive experiments show that our proposed embedding is better in preserving the global geodesic information of graphs, as well as outperforming existing embedding models on directed graphs in a variety of evaluation metrics, in an unsupervised setting.
Cite
@article{arxiv.1905.10227,
title = {Low-dimensional statistical manifold embedding of directed graphs},
author = {Thorben Funke and Tian Guo and Alen Lancic and Nino Antulov-Fantulin},
journal= {arXiv preprint arXiv:1905.10227},
year = {2020}
}
Comments
camera ready version ICLR 2020