Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312998847> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4312998847 abstract "Link prediction, as a representative of network representation learning, is aimed to predict the unknown links between those nodes in the network. Currently, most of the existing approaches are intended for transductive learning. That is to say, even though it is uncertain whether there exists an edge between two nodes, they remain visible in the network. With regard to the prediction of links between the nodes outside the observation network and the nodes within the observation network, the prediction ability of these methods is commonly reduced by the overfitting of known networks, which is a problem made more evident when there is relatively limited information observable in the network. In this paper, the problems arising from inductive link prediction are analyzed to propose a neural network model that can be applied to perform this task. More specifically, a multilayer perceptron is first applied to perform feature transformation. Then, a linear layer with random initialization and locking weights is introduced to improve the model's generalization ability. In addition, both network structure and attribute feature are used to achieve embedding synchronously, while the two kinds of embedding interact with each other through adversarial training. In this way, network structure and attribute information are eventually fused. With the proposed method, the nodes with only attribute information outside the network can also perform the link prediction task with the nodes in the observable network. We conduct a comparative experiment between our method and several existing state-of-the-art methods, and the results showed that our method achieved different degrees of improvement on several datasets." @default.
- W4312998847 created "2023-01-05" @default.
- W4312998847 creator A5000084623 @default.
- W4312998847 creator A5008845730 @default.
- W4312998847 creator A5037536860 @default.
- W4312998847 date "2022-07-18" @default.
- W4312998847 modified "2023-10-17" @default.
- W4312998847 title "Learning node embedding for inductive link prediction in sparse observation network" @default.
- W4312998847 cites W2026417691 @default.
- W4312998847 cites W2027001671 @default.
- W4312998847 cites W2144359569 @default.
- W4312998847 cites W2583803680 @default.
- W4312998847 cites W2808000122 @default.
- W4312998847 cites W2808409763 @default.
- W4312998847 cites W2808987817 @default.
- W4312998847 cites W2962756421 @default.
- W4312998847 cites W3004621088 @default.
- W4312998847 cites W3101485296 @default.
- W4312998847 cites W3104097132 @default.
- W4312998847 cites W3105705953 @default.
- W4312998847 doi "https://doi.org/10.1109/ijcnn55064.2022.9892469" @default.
- W4312998847 hasPublicationYear "2022" @default.
- W4312998847 type Work @default.
- W4312998847 citedByCount "1" @default.
- W4312998847 countsByYear W43129988472023 @default.
- W4312998847 crossrefType "proceedings-article" @default.
- W4312998847 hasAuthorship W4312998847A5000084623 @default.
- W4312998847 hasAuthorship W4312998847A5008845730 @default.
- W4312998847 hasAuthorship W4312998847A5037536860 @default.
- W4312998847 hasConcept C114466953 @default.
- W4312998847 hasConcept C119857082 @default.
- W4312998847 hasConcept C124101348 @default.
- W4312998847 hasConcept C127413603 @default.
- W4312998847 hasConcept C138885662 @default.
- W4312998847 hasConcept C154945302 @default.
- W4312998847 hasConcept C162307627 @default.
- W4312998847 hasConcept C17744445 @default.
- W4312998847 hasConcept C199360897 @default.
- W4312998847 hasConcept C199539241 @default.
- W4312998847 hasConcept C22019652 @default.
- W4312998847 hasConcept C2776359362 @default.
- W4312998847 hasConcept C2776401178 @default.
- W4312998847 hasConcept C2778753846 @default.
- W4312998847 hasConcept C31258907 @default.
- W4312998847 hasConcept C41008148 @default.
- W4312998847 hasConcept C41608201 @default.
- W4312998847 hasConcept C41895202 @default.
- W4312998847 hasConcept C50644808 @default.
- W4312998847 hasConcept C59404180 @default.
- W4312998847 hasConcept C60908668 @default.
- W4312998847 hasConcept C62611344 @default.
- W4312998847 hasConcept C66938386 @default.
- W4312998847 hasConcept C80444323 @default.
- W4312998847 hasConcept C94625758 @default.
- W4312998847 hasConceptScore W4312998847C114466953 @default.
- W4312998847 hasConceptScore W4312998847C119857082 @default.
- W4312998847 hasConceptScore W4312998847C124101348 @default.
- W4312998847 hasConceptScore W4312998847C127413603 @default.
- W4312998847 hasConceptScore W4312998847C138885662 @default.
- W4312998847 hasConceptScore W4312998847C154945302 @default.
- W4312998847 hasConceptScore W4312998847C162307627 @default.
- W4312998847 hasConceptScore W4312998847C17744445 @default.
- W4312998847 hasConceptScore W4312998847C199360897 @default.
- W4312998847 hasConceptScore W4312998847C199539241 @default.
- W4312998847 hasConceptScore W4312998847C22019652 @default.
- W4312998847 hasConceptScore W4312998847C2776359362 @default.
- W4312998847 hasConceptScore W4312998847C2776401178 @default.
- W4312998847 hasConceptScore W4312998847C2778753846 @default.
- W4312998847 hasConceptScore W4312998847C31258907 @default.
- W4312998847 hasConceptScore W4312998847C41008148 @default.
- W4312998847 hasConceptScore W4312998847C41608201 @default.
- W4312998847 hasConceptScore W4312998847C41895202 @default.
- W4312998847 hasConceptScore W4312998847C50644808 @default.
- W4312998847 hasConceptScore W4312998847C59404180 @default.
- W4312998847 hasConceptScore W4312998847C60908668 @default.
- W4312998847 hasConceptScore W4312998847C62611344 @default.
- W4312998847 hasConceptScore W4312998847C66938386 @default.
- W4312998847 hasConceptScore W4312998847C80444323 @default.
- W4312998847 hasConceptScore W4312998847C94625758 @default.
- W4312998847 hasFunder F4320321001 @default.
- W4312998847 hasLocation W43129988471 @default.
- W4312998847 hasOpenAccess W4312998847 @default.
- W4312998847 hasPrimaryLocation W43129988471 @default.
- W4312998847 hasRelatedWork W1486989822 @default.
- W4312998847 hasRelatedWork W1574414179 @default.
- W4312998847 hasRelatedWork W1989422077 @default.
- W4312998847 hasRelatedWork W2118162660 @default.
- W4312998847 hasRelatedWork W2150029999 @default.
- W4312998847 hasRelatedWork W2249059179 @default.
- W4312998847 hasRelatedWork W2922073769 @default.
- W4312998847 hasRelatedWork W4281702477 @default.
- W4312998847 hasRelatedWork W4297676672 @default.
- W4312998847 hasRelatedWork W4362597605 @default.
- W4312998847 isParatext "false" @default.
- W4312998847 isRetracted "false" @default.
- W4312998847 workType "article" @default.