Spectral Embedding of Graph Networks

09/30/2020
by   Shay Deutsch, et al.
0

We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation. The key idea is to transform the given graph into one whose weights measure the centrality of an edge by the fraction of the number of shortest paths that pass through that edge, and employ its spectral proprieties in the representation. Testing the resulting graph network representation shows significant improvement over the sate of the art in data analysis tasks including social networks and material science. We also test our method on node classification from the human-SARS CoV-2 protein-protein interactome.

READ FULL TEXT
research
05/07/2022

Graph Spectral Embedding using the Geodesic Betweeness Centrality

We introduce the Graph Sylvester Embedding (GSE), an unsupervised graph ...
research
01/01/2018

On Spectral Graph Embedding: A Non-Backtracking Perspective and Graph Approximation

Graph embedding has been proven to be efficient and effective in facilit...
research
09/30/2019

Spread-gram: A spreading-activation schema of network structural learning

Network representation learning has exploded recently. However, existing...
research
10/02/2020

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks

One practice of employing deep neural networks is to apply the same arch...
research
06/07/2018

Spectral Network Embedding: A Fast and Scalable Method via Sparsity

Network embedding aims to learn low-dimensional representations of nodes...
research
03/27/2020

The impossibility of low rank representations for triangle-rich complex networks

The study of complex networks is a significant development in modern sci...
research
06/14/2022

SpecNet2: Orthogonalization-free spectral embedding by neural networks

Spectral methods which represent data points by eigenvectors of kernel m...

Please sign up or login with your details

Forgot password? Click here to reset