Low-Dimensional Statistical Manifold Embedding of Directed Graphs


Loading...

Date

2020

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

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 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.

Publication status

published

External links

Editor

Book title

8th International Conference on Learning Representations (ICLR 2020)

Journal / series

Volume

3

Pages / Article No.

2018 - 2035

Publisher

Curran

Event

8th International Conference on Learning Representations (ICLR 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Graphs; Network Embedding; LEARNING ALGORITHMS (MATHEMATICAL STATISTICS); Machine learning (artificial intelligence)

Organisational unit

03784 - Helbing, Dirk / Helbing, Dirk check_circle

Notes

Funding

Related publications and datasets