Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph – a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to 90\%. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.
Epasto, Perozzi - Is a Single Embedding Enough ~ Learning Node Representations that Capture Multiple Social Contexts.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Epasto, Perozzi - Is a Single Embedding Enough ~ Learning Node Representations that Capture Multiple Social Contexts.pdf:application/pdf
%0 Conference Paper
%1 epasto_is_2019
%A Epasto, Alessandro
%A Perozzi, Bryan
%B The World Wide Web Conference on - WWW '19
%C San Francisco, CA, USA
%D 2019
%I ACM Press
%K Embedding_Algorithm Ensemble_Learning Node_Embeddings
%P 394--404
%R 10.1145/3308558.3313660
%T Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts
%U http://dl.acm.org/citation.cfm?doid=3308558.3313660
%X Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph – a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to 90\%. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.
%@ 978-1-4503-6674-8
@inproceedings{epasto_is_2019,
abstract = {Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph – a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to 90\%. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.},
added-at = {2020-02-21T16:09:44.000+0100},
address = {San Francisco, CA, USA},
author = {Epasto, Alessandro and Perozzi, Bryan},
biburl = {https://www.bibsonomy.org/bibtex/2c10acc16d80ebab71087fcfea9f7954f/tschumacher},
booktitle = {The {World} {Wide} {Web} {Conference} on - {WWW} '19},
doi = {10.1145/3308558.3313660},
file = {Epasto, Perozzi - Is a Single Embedding Enough ~ Learning Node Representations that Capture Multiple Social Contexts.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Epasto, Perozzi - Is a Single Embedding Enough ~ Learning Node Representations that Capture Multiple Social Contexts.pdf:application/pdf},
interhash = {b645e8eb0740a608b57b5bfd93ac8bd5},
intrahash = {c10acc16d80ebab71087fcfea9f7954f},
isbn = {978-1-4503-6674-8},
keywords = {Embedding_Algorithm Ensemble_Learning Node_Embeddings},
language = {en},
pages = {394--404},
publisher = {ACM Press},
shorttitle = {Is a {Single} {Embedding} {Enough}?},
timestamp = {2020-02-21T16:09:44.000+0100},
title = {Is a {Single} {Embedding} {Enough}? {Learning} {Node} {Representations} that {Capture} {Multiple} {Social} {Contexts}},
url = {http://dl.acm.org/citation.cfm?doid=3308558.3313660},
urldate = {2019-12-10},
year = 2019
}