Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386001640> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386001640 endingPage "21" @default.
- W4386001640 startingPage "1" @default.
- W4386001640 abstract "Graph attention network can generate effective feature embedding by specifying different weights to different nodes. The key of the research on heterogeneous graph embedding is the way to combine its rich structural information with semantic relations to aggregate the neighborhood information. Most of the existing heterogeneous graph representation learning methods guide the selection of neighbors by defining various meta-paths on heterogeneous graphs. However, these models only consider the information contained in the nodes under different paths and ignore the potential semantic relationships of nodes in different neighbor graph structures, which leads to the underutilization of graph structure information. In this article, we propose a novel adaptive framework named Neighbor Graph Aggregated Graph Attention Network (NGGAN) to fully exploit graph topological details in heterogeneous graph, and aggregates their information to obtain an effective embedding. The key idea is to use different levels of sampling methods to define neighborhood, and use neighbor graphs to represent the complex structural interaction between nodes. In this way, the high-order relationship between nodes and the latent semantics of neighbor graphs can be fully explored. Afterward, a hierarchical attention mechanism is applied to adaptively learn the importance of different objects, including node information, path information, and neighbor graph information. Multiple downstream tasks are performed on four real-world heterogeneous graph datasets, and the experimental results demonstrate the effectiveness of NGGAN." @default.
- W4386001640 created "2023-08-20" @default.
- W4386001640 creator A5007661592 @default.
- W4386001640 creator A5018619642 @default.
- W4386001640 creator A5022802322 @default.
- W4386001640 creator A5041913431 @default.
- W4386001640 creator A5076656594 @default.
- W4386001640 creator A5085556432 @default.
- W4386001640 creator A5087827150 @default.
- W4386001640 date "2023-10-16" @default.
- W4386001640 modified "2023-10-18" @default.
- W4386001640 title "Adaptive Neighbor Graph Aggregated Graph Attention Network for Heterogeneous Graph Embedding" @default.
- W4386001640 cites W103340358 @default.
- W4386001640 cites W2607500032 @default.
- W4386001640 cites W2743104969 @default.
- W4386001640 cites W2767774008 @default.
- W4386001640 cites W2783681041 @default.
- W4386001640 cites W2904890881 @default.
- W4386001640 cites W2911286998 @default.
- W4386001640 cites W2920053406 @default.
- W4386001640 cites W2951626319 @default.
- W4386001640 cites W2954595534 @default.
- W4386001640 cites W2962756421 @default.
- W4386001640 cites W2963169753 @default.
- W4386001640 cites W2963919031 @default.
- W4386001640 cites W2996847713 @default.
- W4386001640 cites W3041319475 @default.
- W4386001640 cites W3042133669 @default.
- W4386001640 cites W3045202147 @default.
- W4386001640 cites W3081203761 @default.
- W4386001640 cites W3104097132 @default.
- W4386001640 cites W3105705953 @default.
- W4386001640 cites W3108202858 @default.
- W4386001640 cites W3114928288 @default.
- W4386001640 cites W3118327669 @default.
- W4386001640 cites W4207072731 @default.
- W4386001640 doi "https://doi.org/10.1145/3616377" @default.
- W4386001640 hasPublicationYear "2023" @default.
- W4386001640 type Work @default.
- W4386001640 citedByCount "0" @default.
- W4386001640 crossrefType "journal-article" @default.
- W4386001640 hasAuthorship W4386001640A5007661592 @default.
- W4386001640 hasAuthorship W4386001640A5018619642 @default.
- W4386001640 hasAuthorship W4386001640A5022802322 @default.
- W4386001640 hasAuthorship W4386001640A5041913431 @default.
- W4386001640 hasAuthorship W4386001640A5076656594 @default.
- W4386001640 hasAuthorship W4386001640A5085556432 @default.
- W4386001640 hasAuthorship W4386001640A5087827150 @default.
- W4386001640 hasBestOaLocation W43860016401 @default.
- W4386001640 hasConcept C124101348 @default.
- W4386001640 hasConcept C132525143 @default.
- W4386001640 hasConcept C154945302 @default.
- W4386001640 hasConcept C203776342 @default.
- W4386001640 hasConcept C22149727 @default.
- W4386001640 hasConcept C41008148 @default.
- W4386001640 hasConcept C41608201 @default.
- W4386001640 hasConcept C64339825 @default.
- W4386001640 hasConcept C75564084 @default.
- W4386001640 hasConcept C80444323 @default.
- W4386001640 hasConceptScore W4386001640C124101348 @default.
- W4386001640 hasConceptScore W4386001640C132525143 @default.
- W4386001640 hasConceptScore W4386001640C154945302 @default.
- W4386001640 hasConceptScore W4386001640C203776342 @default.
- W4386001640 hasConceptScore W4386001640C22149727 @default.
- W4386001640 hasConceptScore W4386001640C41008148 @default.
- W4386001640 hasConceptScore W4386001640C41608201 @default.
- W4386001640 hasConceptScore W4386001640C64339825 @default.
- W4386001640 hasConceptScore W4386001640C75564084 @default.
- W4386001640 hasConceptScore W4386001640C80444323 @default.
- W4386001640 hasFunder F4320321001 @default.
- W4386001640 hasFunder F4320335777 @default.
- W4386001640 hasIssue "1" @default.
- W4386001640 hasLocation W43860016401 @default.
- W4386001640 hasOpenAccess W4386001640 @default.
- W4386001640 hasPrimaryLocation W43860016401 @default.
- W4386001640 hasRelatedWork W2082479932 @default.
- W4386001640 hasRelatedWork W2123605750 @default.
- W4386001640 hasRelatedWork W2601821547 @default.
- W4386001640 hasRelatedWork W2912814903 @default.
- W4386001640 hasRelatedWork W2932872266 @default.
- W4386001640 hasRelatedWork W2950907416 @default.
- W4386001640 hasRelatedWork W3036264823 @default.
- W4386001640 hasRelatedWork W3038102983 @default.
- W4386001640 hasRelatedWork W3169061440 @default.
- W4386001640 hasRelatedWork W3206528106 @default.
- W4386001640 hasVolume "18" @default.
- W4386001640 isParatext "false" @default.
- W4386001640 isRetracted "false" @default.
- W4386001640 workType "article" @default.