DeepWalk: online learning of social representations
B. Perozzi, R. Al-Rfou, und S. Skiena. Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14, Seite 701--710. New York, New York, USA, ACM Press, (2014)
DOI: 10.1145/2623330.2623732
Zusammenfassung
We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs.
Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14
Jahr
2014
Seiten
701--710
Verlag
ACM Press
shorttitle
DeepWalk
isbn
978-1-4503-2956-9
language
en
file
Perozzi et al - DeepWalk ~ Online Learning of Social Representations.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Perozzi et al - DeepWalk ~ Online Learning of Social Representations.pdf:application/pdf
%0 Conference Paper
%1 perozzi_deepwalk:_2014
%A Perozzi, Bryan
%A Al-Rfou, Rami
%A Skiena, Steven
%B Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14
%C New York, New York, USA
%D 2014
%I ACM Press
%K thema thema:deep_walk
%P 701--710
%R 10.1145/2623330.2623732
%T DeepWalk: online learning of social representations
%U http://dl.acm.org/citation.cfm?doid=2623330.2623732
%X We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs.
%@ 978-1-4503-2956-9
@inproceedings{perozzi_deepwalk:_2014,
abstract = {We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs.},
added-at = {2020-10-12T17:05:54.000+0200},
address = {New York, New York, USA},
author = {Perozzi, Bryan and Al-Rfou, Rami and Skiena, Steven},
biburl = {https://www.bibsonomy.org/bibtex/26f91abf7e66309dd5e541b31fab741c9/e.fischer},
booktitle = {Proceedings of the 20th {ACM} {SIGKDD} international conference on {Knowledge} discovery and data mining - {KDD} '14},
doi = {10.1145/2623330.2623732},
file = {Perozzi et al - DeepWalk ~ Online Learning of Social Representations.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Perozzi et al - DeepWalk ~ Online Learning of Social Representations.pdf:application/pdf},
interhash = {17b24764eed4264f26c103f4d3d0d869},
intrahash = {6f91abf7e66309dd5e541b31fab741c9},
isbn = {978-1-4503-2956-9},
keywords = {thema thema:deep_walk},
language = {en},
pages = {701--710},
publisher = {ACM Press},
shorttitle = {{DeepWalk}},
timestamp = {2020-10-16T14:25:27.000+0200},
title = {{DeepWalk}: online learning of social representations},
url = {http://dl.acm.org/citation.cfm?doid=2623330.2623732},
urldate = {2019-12-11},
year = 2014
}