node2coords: Graph Representation Learning with Wasserstein Barycenters

07/31/2020
by   Effrosyni Simou, et al.
0

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn representations that can be interpreted in a straightforward way and that are robust to perturbations to the graph structure. In this work, we address these two limitations by proposing node2coords, a representation learning algorithm for graphs, which learns simultaneously a low-dimensional space and coordinates for the nodes in that space. The patterns that span the low dimensional space reveal the graph's most important structural information. The coordinates of the nodes reveal the proximity of their local structure to the graph structural patterns. In order to measure this proximity by taking into account the underlying graph, we propose to use Wasserstein distances. We introduce an autoencoder that employs a linear layer in the encoder and a novel Wasserstein barycentric layer at the decoder. Node connectivity descriptors, that capture the local structure of the nodes, are passed through the encoder to learn the small set of graph structural patterns. In the decoder, the node connectivity descriptors are reconstructed as Wasserstein barycenters of the graph structural patterns. The optimal weights for the barycenter representation of a node's connectivity descriptor correspond to the coordinates of that node in the low-dimensional space. Experimental results demonstrate that the representations learned with node2coords are interpretable, lead to node embeddings that are stable to perturbations of the graph structure and achieve competitive or superior results compared to state-of-the-art methods in node classification.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/01/2020

Ego-based Entropy Measures for Structural Representations

In complex networks, nodes that share similar structural characteristics...
research
09/15/2020

Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

Unsupervised (or self-supervised) graph representation learning is essen...
research
11/08/2021

Inferential SIR-GN: Scalable Graph Representation Learning

Graph representation learning methods generate numerical vector represen...
research
06/17/2022

Boosting Graph Structure Learning with Dummy Nodes

With the development of graph kernels and graph representation learning,...
research
03/02/2022

Understanding microbiome dynamics via interpretable graph representation learning

Large-scale perturbations in the microbiome constitution are strongly co...
research
06/14/2021

Full interpretable machine learning in 2D with inline coordinates

This paper proposed a new methodology for machine learning in 2-dimensio...
research
07/09/2020

A Generative Graph Method to Solve the Travelling Salesman Problem

The Travelling Salesman Problem (TSP) is a challenging graph task in com...

Please sign up or login with your details

Forgot password? Click here to reset