Modern graph embedding procedures can efficiently process graphs with
millions of nodes. In this paper, we propose GEMSEC -- a graph embedding
algorithm which learns a clustering of the nodes simultaneously with computing
their embedding. GEMSEC is a general extension of earlier work in the domain of
sequence-based graph embedding. GEMSEC places nodes in an abstract feature
space where the vertex features minimize the negative log-likelihood of
preserving sampled vertex neighborhoods, and it incorporates known social
network properties through a machine learning regularization. We present two
new social network datasets and show that by simultaneously considering the
embedding and clustering problems with respect to social properties, GEMSEC
extracts high-quality clusters competitive with or superior to other community
detection algorithms. In experiments, the method is found to be computationally
efficient and robust to the choice of hyperparameters.
Description
[1802.03997] GEMSEC: Graph Embedding with Self Clustering
%0 Generic
%1 rozemberczki2018gemsec
%A Rozemberczki, Benedek
%A Davies, Ryan
%A Sarkar, Rik
%A Sutton, Charles
%D 2018
%K cluster embedding graph network social
%T GEMSEC: Graph Embedding with Self Clustering
%U http://arxiv.org/abs/1802.03997
%X Modern graph embedding procedures can efficiently process graphs with
millions of nodes. In this paper, we propose GEMSEC -- a graph embedding
algorithm which learns a clustering of the nodes simultaneously with computing
their embedding. GEMSEC is a general extension of earlier work in the domain of
sequence-based graph embedding. GEMSEC places nodes in an abstract feature
space where the vertex features minimize the negative log-likelihood of
preserving sampled vertex neighborhoods, and it incorporates known social
network properties through a machine learning regularization. We present two
new social network datasets and show that by simultaneously considering the
embedding and clustering problems with respect to social properties, GEMSEC
extracts high-quality clusters competitive with or superior to other community
detection algorithms. In experiments, the method is found to be computationally
efficient and robust to the choice of hyperparameters.
@misc{rozemberczki2018gemsec,
abstract = {Modern graph embedding procedures can efficiently process graphs with
millions of nodes. In this paper, we propose GEMSEC -- a graph embedding
algorithm which learns a clustering of the nodes simultaneously with computing
their embedding. GEMSEC is a general extension of earlier work in the domain of
sequence-based graph embedding. GEMSEC places nodes in an abstract feature
space where the vertex features minimize the negative log-likelihood of
preserving sampled vertex neighborhoods, and it incorporates known social
network properties through a machine learning regularization. We present two
new social network datasets and show that by simultaneously considering the
embedding and clustering problems with respect to social properties, GEMSEC
extracts high-quality clusters competitive with or superior to other community
detection algorithms. In experiments, the method is found to be computationally
efficient and robust to the choice of hyperparameters.},
added-at = {2020-05-24T17:32:25.000+0200},
author = {Rozemberczki, Benedek and Davies, Ryan and Sarkar, Rik and Sutton, Charles},
biburl = {https://www.bibsonomy.org/bibtex/283e82181b008828d743efa88e070bd9f/parismic},
description = {[1802.03997] GEMSEC: Graph Embedding with Self Clustering},
interhash = {faad8c3891f441da5b1808a0b3e3495d},
intrahash = {83e82181b008828d743efa88e070bd9f},
keywords = {cluster embedding graph network social},
note = {cite arxiv:1802.03997},
timestamp = {2020-05-24T17:32:25.000+0200},
title = {GEMSEC: Graph Embedding with Self Clustering},
url = {http://arxiv.org/abs/1802.03997},
year = 2018
}