@misc{pan2018adversarially,
  abstract = {Graph embedding is an effective method to represent graph data in a low
dimensional space for graph analytics. Most existing embedding algorithms
typically focus on preserving the topological structure or minimizing the
reconstruction errors of graph data, but they have mostly ignored the data
distribution of the latent codes from the graphs, which often results in
inferior embedding in real-world graph data. In this paper, we propose a novel
adversarial graph embedding framework for graph data. The framework encodes the
topological structure and node content in a graph to a compact representation,
on which a decoder is trained to reconstruct the graph structure. Furthermore,
the latent representation is enforced to match a prior distribution via an
adversarial training scheme. To learn a robust embedding, two variants of
adversarial approaches, adversarially regularized graph autoencoder (ARGA) and
adversarially regularized variational graph autoencoder (ARVGA), are developed.
Experimental studies on real-world graphs validate our design and demonstrate
that our algorithms outperform baselines by a wide margin in link prediction,
graph clustering, and graph visualization tasks.},
  added-at = {2018-02-14T21:20:34.000+0100},
  author = {Pan, Shirui and Hu, Ruiqi and Long, Guodong and Jiang, Jing and Yao, Lina and Zhang, Chengqi},
  biburl = {https://www.bibsonomy.org/bibtex/2b24ed094ff79752832f384b671c36b2a/jk_itwm},
  description = {Adversarially Regularized Graph Autoencoder},
  interhash = {f729e106bb4b5fd3e116cf58d96a5b05},
  intrahash = {b24ed094ff79752832f384b671c36b2a},
  keywords = {autoencoder graph},
  note = {cite arxiv:1802.04407},
  timestamp = {2018-02-14T21:20:34.000+0100},
  title = {Adversarially Regularized Graph Autoencoder},
  url = {http://arxiv.org/abs/1802.04407},
  year = 2018
}

{"_id":"XxuEebkBavvnzbPey","bibbaseid":"pan-hu-long-jiang-yao-zhang-adversariallyregularizedgraphautoencoder-2018","authorIDs":["561c75c18d7cb332200004ce","FgTRy7pNrBNcDn5rk"],"author_short":["Pan, S.","Hu, R.","Long, G.","Jiang, J.","Yao, L.","Zhang, C."],"bibdata":{"bibtype":"misc","type":"misc","abstract":"Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.","added-at":"2018-02-14T21:20:34.000+0100","author":[{"propositions":[],"lastnames":["Pan"],"firstnames":["Shirui"],"suffixes":[]},{"propositions":[],"lastnames":["Hu"],"firstnames":["Ruiqi"],"suffixes":[]},{"propositions":[],"lastnames":["Long"],"firstnames":["Guodong"],"suffixes":[]},{"propositions":[],"lastnames":["Jiang"],"firstnames":["Jing"],"suffixes":[]},{"propositions":[],"lastnames":["Yao"],"firstnames":["Lina"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Chengqi"],"suffixes":[]}],"biburl":"https://www.bibsonomy.org/bibtex/2b24ed094ff79752832f384b671c36b2a/jk_itwm","description":"Adversarially Regularized Graph Autoencoder","interhash":"f729e106bb4b5fd3e116cf58d96a5b05","intrahash":"b24ed094ff79752832f384b671c36b2a","keywords":"autoencoder graph","note":"cite arxiv:1802.04407","timestamp":"2018-02-14T21:20:34.000+0100","title":"Adversarially Regularized Graph Autoencoder","url":"http://arxiv.org/abs/1802.04407","year":"2018","bibtex":"@misc{pan2018adversarially,\n abstract = {Graph embedding is an effective method to represent graph data in a low\r\ndimensional space for graph analytics. Most existing embedding algorithms\r\ntypically focus on preserving the topological structure or minimizing the\r\nreconstruction errors of graph data, but they have mostly ignored the data\r\ndistribution of the latent codes from the graphs, which often results in\r\ninferior embedding in real-world graph data. In this paper, we propose a novel\r\nadversarial graph embedding framework for graph data. The framework encodes the\r\ntopological structure and node content in a graph to a compact representation,\r\non which a decoder is trained to reconstruct the graph structure. Furthermore,\r\nthe latent representation is enforced to match a prior distribution via an\r\nadversarial training scheme. To learn a robust embedding, two variants of\r\nadversarial approaches, adversarially regularized graph autoencoder (ARGA) and\r\nadversarially regularized variational graph autoencoder (ARVGA), are developed.\r\nExperimental studies on real-world graphs validate our design and demonstrate\r\nthat our algorithms outperform baselines by a wide margin in link prediction,\r\ngraph clustering, and graph visualization tasks.},\n added-at = {2018-02-14T21:20:34.000+0100},\n author = {Pan, Shirui and Hu, Ruiqi and Long, Guodong and Jiang, Jing and Yao, Lina and Zhang, Chengqi},\n biburl = {https://www.bibsonomy.org/bibtex/2b24ed094ff79752832f384b671c36b2a/jk_itwm},\n description = {Adversarially Regularized Graph Autoencoder},\n interhash = {f729e106bb4b5fd3e116cf58d96a5b05},\n intrahash = {b24ed094ff79752832f384b671c36b2a},\n keywords = {autoencoder graph},\n note = {cite arxiv:1802.04407},\n timestamp = {2018-02-14T21:20:34.000+0100},\n title = {Adversarially Regularized Graph Autoencoder},\n url = {http://arxiv.org/abs/1802.04407},\n year = 2018\n}\n\n","author_short":["Pan, S.","Hu, R.","Long, G.","Jiang, J.","Yao, L.","Zhang, C."],"key":"pan2018adversarially","id":"pan2018adversarially","bibbaseid":"pan-hu-long-jiang-yao-zhang-adversariallyregularizedgraphautoencoder-2018","role":"author","urls":{"Paper":"http://arxiv.org/abs/1802.04407"},"keyword":["autoencoder graph"],"metadata":{"authorlinks":{"pan, s":"https://shiruipan.github.io/post/selectedpub/"}},"downloads":0},"bibtype":"misc","biburl":"http://www.bibsonomy.org/bib/author/pan, shirui?items=1000","creationDate":"2019-11-29T05:29:58.857Z","downloads":0,"keywords":["autoencoder graph"],"search_terms":["adversarially","regularized","graph","autoencoder","pan","hu","long","jiang","yao","zhang"],"title":"Adversarially Regularized Graph Autoencoder","year":2018,"dataSources":["mKA5vx6kcS6ikoYhW","AoeZNpAr9D2ciGMwa"]}