%0 Conference Paper %1 cao_grarep:_2015 %A Cao, Shaosheng %A Lu, Wei %A Xu, Qiongkai %B Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15 %C Melbourne, Australia %D 2015 %I ACM Press %K Embedding_Algorithm Matrix_Factorization Node_Embeddings %P 891--900 %R 10.1145/2806416.2806512 %T GraRep: Learning Graph Representations with Global Structural Information %U http://dl.acm.org/citation.cfm?doid=2806416.2806512 %X In this paper, we present GraRep, a novel model for learning vertex representations of weighted graphs. This model learns low dimensional vectors to represent vertices appearing in a graph and, unlike existing work, integrates global structural information of the graph into the learning process. We also formally analyze the connections between our work and several previous research efforts, including the DeepWalk model of Perozzi et al. 20 as well as the skip-gram model with negative sampling of Mikolov et al. 18 We conduct experiments on a language network, a social network as well as a citation network and show that our learned global representations can be effectively used as features in tasks such as clustering, classification and visualization. Empirical results demonstrate that our representation significantly outperforms other state-of-the-art methods in such tasks. %@ 978-1-4503-3794-6

@inproceedings{cao_grarep:_2015, abstract = {In this paper, we present GraRep, a novel model for learning vertex representations of weighted graphs. This model learns low dimensional vectors to represent vertices appearing in a graph and, unlike existing work, integrates global structural information of the graph into the learning process. We also formally analyze the connections between our work and several previous research efforts, including the DeepWalk model of Perozzi et al. [20] as well as the skip-gram model with negative sampling of Mikolov et al. [18] We conduct experiments on a language network, a social network as well as a citation network and show that our learned global representations can be effectively used as features in tasks such as clustering, classification and visualization. Empirical results demonstrate that our representation significantly outperforms other state-of-the-art methods in such tasks.}, added-at = {2020-02-21T16:09:44.000+0100}, address = {Melbourne, Australia}, author = {Cao, Shaosheng and Lu, Wei and Xu, Qiongkai}, biburl = {https://www.bibsonomy.org/bibtex/2f8047de3d6a0d2ce52e29752250258a5/tschumacher}, booktitle = {Proceedings of the 24th {ACM} {International} on {Conference} on {Information} and {Knowledge} {Management} - {CIKM} '15}, doi = {10.1145/2806416.2806512}, file = {Cao et al - GraRep ~ Learning Graph Representations with Global Structural Information.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Cao et al - GraRep ~ Learning Graph Representations with Global Structural Information.pdf:application/pdf}, interhash = {1e937f3a0805ac51313ed3deeb9eb4f7}, intrahash = {f8047de3d6a0d2ce52e29752250258a5}, isbn = {978-1-4503-3794-6}, keywords = {Embedding_Algorithm Matrix_Factorization Node_Embeddings}, language = {en}, pages = {891--900}, publisher = {ACM Press}, shorttitle = {{GraRep}}, timestamp = {2020-02-21T16:09:44.000+0100}, title = {{GraRep}: {Learning} {Graph} {Representations} with {Global} {Structural} {Information}}, url = {http://dl.acm.org/citation.cfm?doid=2806416.2806512}, urldate = {2019-12-10}, year = 2015 }