Matches in SemOpenAlex for { <https://semopenalex.org/work/W2550241572> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2550241572 abstract "Graphs provide a powerful means for representing complex interactions between entities. Recently, deep learning approaches are emerging for representing and modeling graph-structured data, although the conventional deep learning methods (such as convolutional neural networks and recurrent neural networks) have mainly focused on grid-structured inputs (image and audio). Leveraged by the capability of representation learning, deep learning based techniques are reporting promising results for graph applications by detecting structural characteristics of graphs in an automated fashion. In this paper, we attempt to advance deep learning for graph-structured data by incorporating another component, transfer learning. By transferring the intrinsic geometric information learned in the source domain, our approach can help us to construct a model for a new but related task in the target domain without collecting new data and without training a new model from scratch. We thoroughly test our approach with large-scale real corpora and confirm the effectiveness of the proposed transfer learning framework for deep learning on graphs. According to our experiments, transfer learning is most effective when the source and target domains bear a high level of structural similarity in their graph representations." @default.
- W2550241572 created "2016-11-30" @default.
- W2550241572 creator A5011313652 @default.
- W2550241572 creator A5014903441 @default.
- W2550241572 creator A5023696368 @default.
- W2550241572 creator A5086877012 @default.
- W2550241572 date "2016-11-15" @default.
- W2550241572 modified "2023-09-27" @default.
- W2550241572 title "Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets" @default.
- W2550241572 cites W1481933820 @default.
- W2550241572 cites W1519532587 @default.
- W2550241572 cites W1662382123 @default.
- W2550241572 cites W1904633530 @default.
- W2550241572 cites W1951806617 @default.
- W2550241572 cites W2016423476 @default.
- W2550241572 cites W2076063813 @default.
- W2550241572 cites W2101491865 @default.
- W2550241572 cites W2121244641 @default.
- W2550241572 cites W2131829632 @default.
- W2550241572 cites W2133299088 @default.
- W2550241572 cites W2165698076 @default.
- W2550241572 cites W2176353499 @default.
- W2550241572 cites W2244807774 @default.
- W2550241572 cites W2247728953 @default.
- W2550241572 cites W2257979135 @default.
- W2550241572 cites W2919115771 @default.
- W2550241572 cites W2949888546 @default.
- W2550241572 cites W2963371736 @default.
- W2550241572 cites W637153065 @default.
- W2550241572 hasPublicationYear "2016" @default.
- W2550241572 type Work @default.
- W2550241572 sameAs 2550241572 @default.
- W2550241572 citedByCount "0" @default.
- W2550241572 crossrefType "posted-content" @default.
- W2550241572 hasAuthorship W2550241572A5011313652 @default.
- W2550241572 hasAuthorship W2550241572A5014903441 @default.
- W2550241572 hasAuthorship W2550241572A5023696368 @default.
- W2550241572 hasAuthorship W2550241572A5086877012 @default.
- W2550241572 hasConcept C108583219 @default.
- W2550241572 hasConcept C119857082 @default.
- W2550241572 hasConcept C132525143 @default.
- W2550241572 hasConcept C150899416 @default.
- W2550241572 hasConcept C154945302 @default.
- W2550241572 hasConcept C162324750 @default.
- W2550241572 hasConcept C187736073 @default.
- W2550241572 hasConcept C188888258 @default.
- W2550241572 hasConcept C19966478 @default.
- W2550241572 hasConcept C2780451532 @default.
- W2550241572 hasConcept C28006648 @default.
- W2550241572 hasConcept C41008148 @default.
- W2550241572 hasConcept C59404180 @default.
- W2550241572 hasConcept C77075516 @default.
- W2550241572 hasConcept C80444323 @default.
- W2550241572 hasConcept C81363708 @default.
- W2550241572 hasConcept C90509273 @default.
- W2550241572 hasConceptScore W2550241572C108583219 @default.
- W2550241572 hasConceptScore W2550241572C119857082 @default.
- W2550241572 hasConceptScore W2550241572C132525143 @default.
- W2550241572 hasConceptScore W2550241572C150899416 @default.
- W2550241572 hasConceptScore W2550241572C154945302 @default.
- W2550241572 hasConceptScore W2550241572C162324750 @default.
- W2550241572 hasConceptScore W2550241572C187736073 @default.
- W2550241572 hasConceptScore W2550241572C188888258 @default.
- W2550241572 hasConceptScore W2550241572C19966478 @default.
- W2550241572 hasConceptScore W2550241572C2780451532 @default.
- W2550241572 hasConceptScore W2550241572C28006648 @default.
- W2550241572 hasConceptScore W2550241572C41008148 @default.
- W2550241572 hasConceptScore W2550241572C59404180 @default.
- W2550241572 hasConceptScore W2550241572C77075516 @default.
- W2550241572 hasConceptScore W2550241572C80444323 @default.
- W2550241572 hasConceptScore W2550241572C81363708 @default.
- W2550241572 hasConceptScore W2550241572C90509273 @default.
- W2550241572 hasLocation W25502415721 @default.
- W2550241572 hasOpenAccess W2550241572 @default.
- W2550241572 hasPrimaryLocation W25502415721 @default.
- W2550241572 hasRelatedWork W2604545383 @default.
- W2550241572 hasRelatedWork W2942259124 @default.
- W2550241572 hasRelatedWork W2946117866 @default.
- W2550241572 hasRelatedWork W2947372801 @default.
- W2550241572 hasRelatedWork W2962956528 @default.
- W2550241572 hasRelatedWork W2977118937 @default.
- W2550241572 hasRelatedWork W2979535968 @default.
- W2550241572 hasRelatedWork W2981401872 @default.
- W2550241572 hasRelatedWork W2987063230 @default.
- W2550241572 hasRelatedWork W3003206728 @default.
- W2550241572 hasRelatedWork W3006198072 @default.
- W2550241572 hasRelatedWork W3037456060 @default.
- W2550241572 hasRelatedWork W3093151423 @default.
- W2550241572 hasRelatedWork W3124027051 @default.
- W2550241572 hasRelatedWork W3134296944 @default.
- W2550241572 hasRelatedWork W3171553042 @default.
- W2550241572 hasRelatedWork W3176939811 @default.
- W2550241572 hasRelatedWork W3185645213 @default.
- W2550241572 hasRelatedWork W3195415198 @default.
- W2550241572 hasRelatedWork W3205205408 @default.
- W2550241572 isParatext "false" @default.
- W2550241572 isRetracted "false" @default.
- W2550241572 magId "2550241572" @default.
- W2550241572 workType "article" @default.