Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102843349> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3102843349 abstract "When dealing with the graph data in real problems, only part of the nodes in the graph are labeled and the rest are not. A core problem is how to use this information to extend the labeling so that all nodes are assigned a label (or labels). Intuitively we can learn the patterns (or extract some representations) from those labeled nodes and then apply the patterns to determine the membership for those unknown nodes. A majority of previous related studies focus on extracting the local information representations and may suffer from lack of additional constraints which are necessary for improving the robustness of representation. In this work, we presented Graph- embedding enhanced attention Adversarial Autoencoder Networks (Great AAN), a new scalable generalized framework for graph-structured data representation learning and node classification. In our framework, we firstly introduce the attention layers and provide insights on the self-attention mechanism with multi-heads. Moreover, the shortest path length between nodes is incorporated into the self-attention mechanism to enhance the embedding of the node’s structural spatial information. Then a generative adversarial autoencoder is proposed to encode both global and local information and enhance the robustness of the embedded data distribution. Due to the scalability of our approach, it has efficient and various applications, including node classification, a recommendation system, and graph link prediction. We applied this Great AAN on multiple datasets (including PPI, Cora, Citeseer, Pubmed and Alipay) from social science and biomedical science. The experimental results demonstrated that our new framework significantly outperforms several popular methods." @default.
- W3102843349 created "2020-11-23" @default.
- W3102843349 creator A5026310549 @default.
- W3102843349 date "2020-09-27" @default.
- W3102843349 modified "2023-09-23" @default.
- W3102843349 title "Graph-embedding Enhanced Attention Adversarial Autoencoder" @default.
- W3102843349 hasPublicationYear "2020" @default.
- W3102843349 type Work @default.
- W3102843349 sameAs 3102843349 @default.
- W3102843349 citedByCount "0" @default.
- W3102843349 crossrefType "journal-article" @default.
- W3102843349 hasAuthorship W3102843349A5026310549 @default.
- W3102843349 hasConcept C101738243 @default.
- W3102843349 hasConcept C104317684 @default.
- W3102843349 hasConcept C108583219 @default.
- W3102843349 hasConcept C119857082 @default.
- W3102843349 hasConcept C124101348 @default.
- W3102843349 hasConcept C132525143 @default.
- W3102843349 hasConcept C154945302 @default.
- W3102843349 hasConcept C185592680 @default.
- W3102843349 hasConcept C37736160 @default.
- W3102843349 hasConcept C41008148 @default.
- W3102843349 hasConcept C41608201 @default.
- W3102843349 hasConcept C48044578 @default.
- W3102843349 hasConcept C55493867 @default.
- W3102843349 hasConcept C59404180 @default.
- W3102843349 hasConcept C63479239 @default.
- W3102843349 hasConcept C66746571 @default.
- W3102843349 hasConcept C75564084 @default.
- W3102843349 hasConcept C77088390 @default.
- W3102843349 hasConcept C80444323 @default.
- W3102843349 hasConceptScore W3102843349C101738243 @default.
- W3102843349 hasConceptScore W3102843349C104317684 @default.
- W3102843349 hasConceptScore W3102843349C108583219 @default.
- W3102843349 hasConceptScore W3102843349C119857082 @default.
- W3102843349 hasConceptScore W3102843349C124101348 @default.
- W3102843349 hasConceptScore W3102843349C132525143 @default.
- W3102843349 hasConceptScore W3102843349C154945302 @default.
- W3102843349 hasConceptScore W3102843349C185592680 @default.
- W3102843349 hasConceptScore W3102843349C37736160 @default.
- W3102843349 hasConceptScore W3102843349C41008148 @default.
- W3102843349 hasConceptScore W3102843349C41608201 @default.
- W3102843349 hasConceptScore W3102843349C48044578 @default.
- W3102843349 hasConceptScore W3102843349C55493867 @default.
- W3102843349 hasConceptScore W3102843349C59404180 @default.
- W3102843349 hasConceptScore W3102843349C63479239 @default.
- W3102843349 hasConceptScore W3102843349C66746571 @default.
- W3102843349 hasConceptScore W3102843349C75564084 @default.
- W3102843349 hasConceptScore W3102843349C77088390 @default.
- W3102843349 hasConceptScore W3102843349C80444323 @default.
- W3102843349 hasLocation W31028433491 @default.
- W3102843349 hasOpenAccess W3102843349 @default.
- W3102843349 hasPrimaryLocation W31028433491 @default.
- W3102843349 hasRelatedWork W2765425003 @default.
- W3102843349 hasRelatedWork W2766453196 @default.
- W3102843349 hasRelatedWork W2785456199 @default.
- W3102843349 hasRelatedWork W2935184916 @default.
- W3102843349 hasRelatedWork W2942587884 @default.
- W3102843349 hasRelatedWork W2946250457 @default.
- W3102843349 hasRelatedWork W2951269871 @default.
- W3102843349 hasRelatedWork W2980117048 @default.
- W3102843349 hasRelatedWork W2989985603 @default.
- W3102843349 hasRelatedWork W3009525938 @default.
- W3102843349 hasRelatedWork W3022669437 @default.
- W3102843349 hasRelatedWork W3082154031 @default.
- W3102843349 hasRelatedWork W3114898837 @default.
- W3102843349 hasRelatedWork W3126928293 @default.
- W3102843349 hasRelatedWork W3128129382 @default.
- W3102843349 hasRelatedWork W3130747874 @default.
- W3102843349 hasRelatedWork W3157127187 @default.
- W3102843349 hasRelatedWork W3158141616 @default.
- W3102843349 hasRelatedWork W3166679531 @default.
- W3102843349 hasRelatedWork W3210265791 @default.
- W3102843349 isParatext "false" @default.
- W3102843349 isRetracted "false" @default.
- W3102843349 magId "3102843349" @default.
- W3102843349 workType "article" @default.