Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132713817> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3132713817 abstract "Graph neural networks have been paid a lot attentions in recent years since many real-word data can naturally be represented by graph structures. Graph neural networks such as GCNs and GATs mainly focus on node features while ignoring edge features in graphs. However, in many graph structure data such as knowledge graphs, social networks, edge features are also important as they contain vital information about relations between nodes which are commonly ignored or simplified into binary or scalar values by existing methods. In this work we build a novel learning method on graphs called GNN-EE, i.e. GNN with Edge Enhanced, which takes both the node features and edge features into account while updating representations of graph components and can be applied to most of the common graph neural networks such as GCNs and GATs. Our GNN-EE method fits in the message-passing framework and thus is easy to generalize. In addition, we extend the random-walk-based algorithms on graphs so that they can consider both node and edge features on graphs. We use those random-walk-based algorithms as a pre-training method on graph with few initial features. We demonstrate the effectiveness and flexibility of our GNN-EE method through entity classification tasks and graph classification tasks." @default.
- W3132713817 created "2021-03-01" @default.
- W3132713817 creator A5021539873 @default.
- W3132713817 creator A5051552380 @default.
- W3132713817 creator A5058743657 @default.
- W3132713817 date "2020-12-11" @default.
- W3132713817 modified "2023-09-23" @default.
- W3132713817 title "Enhancing Graph Neural Networks with Edge Features Through Sequential Representation" @default.
- W3132713817 cites W2025956887 @default.
- W3132713817 cites W2087159174 @default.
- W3132713817 cites W2142498761 @default.
- W3132713817 cites W2194775991 @default.
- W3132713817 cites W2250539671 @default.
- W3132713817 cites W2521492858 @default.
- W3132713817 cites W2523679382 @default.
- W3132713817 cites W2604314403 @default.
- W3132713817 cites W2759336060 @default.
- W3132713817 cites W2788919350 @default.
- W3132713817 cites W2899771611 @default.
- W3132713817 cites W2952254971 @default.
- W3132713817 cites W2962711740 @default.
- W3132713817 cites W2962756421 @default.
- W3132713817 cites W2964145825 @default.
- W3132713817 cites W2971933740 @default.
- W3132713817 cites W2995448904 @default.
- W3132713817 cites W3104097132 @default.
- W3132713817 doi "https://doi.org/10.1109/iccc51575.2020.9345090" @default.
- W3132713817 hasPublicationYear "2020" @default.
- W3132713817 type Work @default.
- W3132713817 sameAs 3132713817 @default.
- W3132713817 citedByCount "1" @default.
- W3132713817 countsByYear W31327138172023 @default.
- W3132713817 crossrefType "proceedings-article" @default.
- W3132713817 hasAuthorship W3132713817A5021539873 @default.
- W3132713817 hasAuthorship W3132713817A5051552380 @default.
- W3132713817 hasAuthorship W3132713817A5058743657 @default.
- W3132713817 hasConcept C105795698 @default.
- W3132713817 hasConcept C121194460 @default.
- W3132713817 hasConcept C132525143 @default.
- W3132713817 hasConcept C154945302 @default.
- W3132713817 hasConcept C33923547 @default.
- W3132713817 hasConcept C41008148 @default.
- W3132713817 hasConcept C50644808 @default.
- W3132713817 hasConcept C80444323 @default.
- W3132713817 hasConceptScore W3132713817C105795698 @default.
- W3132713817 hasConceptScore W3132713817C121194460 @default.
- W3132713817 hasConceptScore W3132713817C132525143 @default.
- W3132713817 hasConceptScore W3132713817C154945302 @default.
- W3132713817 hasConceptScore W3132713817C33923547 @default.
- W3132713817 hasConceptScore W3132713817C41008148 @default.
- W3132713817 hasConceptScore W3132713817C50644808 @default.
- W3132713817 hasConceptScore W3132713817C80444323 @default.
- W3132713817 hasFunder F4320321001 @default.
- W3132713817 hasFunder F4320327912 @default.
- W3132713817 hasLocation W31327138171 @default.
- W3132713817 hasOpenAccess W3132713817 @default.
- W3132713817 hasPrimaryLocation W31327138171 @default.
- W3132713817 hasRelatedWork W2151399529 @default.
- W3132713817 hasRelatedWork W2890855364 @default.
- W3132713817 hasRelatedWork W2891771806 @default.
- W3132713817 hasRelatedWork W2892310698 @default.
- W3132713817 hasRelatedWork W2952419077 @default.
- W3132713817 hasRelatedWork W3120865897 @default.
- W3132713817 hasRelatedWork W4210836535 @default.
- W3132713817 hasRelatedWork W4281693073 @default.
- W3132713817 hasRelatedWork W4286857724 @default.
- W3132713817 hasRelatedWork W4372260176 @default.
- W3132713817 isParatext "false" @default.
- W3132713817 isRetracted "false" @default.
- W3132713817 magId "3132713817" @default.
- W3132713817 workType "article" @default.