Kernel Node Embeddings

09/08/2019
by   Abdulkadir Çelikkanat, et al.
0

Learning representations of nodes in a low dimensional space is a crucial task with many interesting applications in network analysis, including link prediction and node classification. Two popular approaches for this problem include matrix factorization and random walk-based models. In this paper, we aim to bring together the best of both worlds, towards learning latent node representations. In particular, we propose a weighted matrix factorization model which encodes random walk-based information about the nodes of the graph. The main benefit of this formulation is that it allows to utilize kernel functions on the computation of the embeddings. We perform an empirical evaluation on real-world networks, showing that the proposed model outperforms baseline node embedding algorithms in two downstream machine learning tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/09/2021

Multiple Kernel Representation Learning on Networks

Learning representations of nodes in a low dimensional space is a crucia...
research
11/20/2019

Exponential Family Graph Embeddings

Representing networks in a low dimensional latent space is a crucial tas...
research
11/11/2017

Generalized Neural Graph Embedding with Matrix Factorization

Recent advances in language modeling such as word2vec motivate a number ...
research
10/01/2020

N odeS ig: Random Walk Diffusion meets Hashing for Scalable Graph Embeddings

Learning node representations is a crucial task with a plethora of inter...
research
08/12/2019

RWR-GAE: Random Walk Regularization for Graph Auto Encoders

Node embeddings have become an ubiquitous technique for representing gra...
research
03/19/2019

A Comprehensive Comparison of Unsupervised Network Representation Learning Methods

There has been appreciable progress in unsupervised network representati...
research
11/16/2020

Graph embeddings via matrix factorization for link prediction: smoothing or truncating negatives?

Link prediction – the process of uncovering missing links in a complex n...

Please sign up or login with your details

Forgot password? Click here to reset