Residual2Vec: Debiasing graph embedding with random graphs

10/14/2021
by   Sadamori Kojaku, et al.
11

Graph embedding maps a graph into a convenient vector-space representation for graph analysis and machine learning applications. Many graph embedding methods hinge on a sampling of context nodes based on random walks. However, random walks can be a biased sampler due to the structural properties of graphs. Most notably, random walks are biased by the degree of each node, where a node is sampled proportionally to its degree. The implication of such biases has not been clear, particularly in the context of graph representation learning. Here, we investigate the impact of the random walks' bias on graph embedding and propose residual2vec, a general graph embedding method that can debias various structural biases in graphs by using random graphs. We demonstrate that this debiasing not only improves link prediction and clustering performance but also allows us to explicitly model salient structural properties in graph embedding.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2022

A Representation Learning Framework for Property Graphs

Representation learning on graphs, also called graph embedding, has demo...
research
05/19/2020

Learning Representations using Spectral-Biased Random Walks on Graphs

Several state-of-the-art neural graph embedding methods are based on sho...
research
03/02/2018

NetGAN: Generating Graphs via Random Walks

We propose NetGAN - the first implicit generative model for graphs able ...
research
07/05/2019

Network Embedding: on Compression and Learning

Recently, network embedding that encodes structural information of graph...
research
01/02/2021

Compatibility, embedding and regularization of non-local random walks on graphs

Several variants of the graph Laplacian have been introduced to model no...
research
07/01/2020

Build2Vec: Building Representation in Vector Space

In this paper, we represent a methodology of a graph embeddings algorith...
research
10/04/2019

Targeted sampling from massive Blockmodel graphs with personalized PageRank

This paper provides statistical theory and intuition for Personalized Pa...

Please sign up or login with your details

Forgot password? Click here to reset