Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966567766> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2966567766 abstract "The success of graph convolutional neural networks (GCNNs) based semi-supervised node classification is credited to the attribute smoothing (propagating) over the topology. However, the attributes may be interfered by the utilization of the topology information. This distortion will induce a certain amount of misclassifications of the nodes, which can be correctly predicted with only the attributes. By analyzing the impact of the edges in attribute propagations, the simple edges, which connect two nodes with similar attributes, should be given priority during the training process compared to the complex ones according to curriculum learning. To reduce the distortions induced by the topology while exploit more potentials of the attribute information, Dual Self-Paced Graph Convolutional Network (DSP-GCN) is proposed in this paper. Specifically, the unlabelled nodes with confidently predicted labels are gradually added into the training set in the node-level self-paced learning, while edges are gradually, from the simple edges to the complex ones, added into the graph during the training process in the edge-level self-paced learning. These two learning strategies are designed to mutually reinforce each other by coupling the selections of the edges and unlabelled nodes. Experimental results of transductive semi-supervised node classification on many real networks indicate that the proposed DSP-GCN has successfully reduced the attribute distortions induced by the topology while it gives superior performances with only one graph convolutional layer." @default.
- W2966567766 created "2019-08-13" @default.
- W2966567766 creator A5003769188 @default.
- W2966567766 creator A5005845073 @default.
- W2966567766 creator A5030187602 @default.
- W2966567766 creator A5032503755 @default.
- W2966567766 date "2019-08-01" @default.
- W2966567766 modified "2023-10-12" @default.
- W2966567766 title "Dual Self-Paced Graph Convolutional Network: Towards Reducing Attribute Distortions Induced by Topology" @default.
- W2966567766 cites W1512387364 @default.
- W2966567766 cites W1983320747 @default.
- W2966567766 cites W2104290444 @default.
- W2966567766 cites W2106545428 @default.
- W2966567766 cites W2119998616 @default.
- W2966567766 cites W2132984949 @default.
- W2966567766 cites W2136504847 @default.
- W2966567766 cites W2558460151 @default.
- W2966567766 cites W2604745395 @default.
- W2966567766 cites W2624431344 @default.
- W2966567766 cites W2740306440 @default.
- W2966567766 cites W2809001617 @default.
- W2966567766 cites W2809503262 @default.
- W2966567766 cites W2963312446 @default.
- W2966567766 cites W2964321699 @default.
- W2966567766 doi "https://doi.org/10.24963/ijcai.2019/564" @default.
- W2966567766 hasPublicationYear "2019" @default.
- W2966567766 type Work @default.
- W2966567766 sameAs 2966567766 @default.
- W2966567766 citedByCount "15" @default.
- W2966567766 countsByYear W29665677662019 @default.
- W2966567766 countsByYear W29665677662020 @default.
- W2966567766 countsByYear W29665677662021 @default.
- W2966567766 countsByYear W29665677662022 @default.
- W2966567766 countsByYear W29665677662023 @default.
- W2966567766 crossrefType "proceedings-article" @default.
- W2966567766 hasAuthorship W2966567766A5003769188 @default.
- W2966567766 hasAuthorship W2966567766A5005845073 @default.
- W2966567766 hasAuthorship W2966567766A5030187602 @default.
- W2966567766 hasAuthorship W2966567766A5032503755 @default.
- W2966567766 hasBestOaLocation W29665677661 @default.
- W2966567766 hasConcept C114614502 @default.
- W2966567766 hasConcept C127413603 @default.
- W2966567766 hasConcept C132525143 @default.
- W2966567766 hasConcept C154945302 @default.
- W2966567766 hasConcept C184720557 @default.
- W2966567766 hasConcept C199845137 @default.
- W2966567766 hasConcept C31258907 @default.
- W2966567766 hasConcept C33923547 @default.
- W2966567766 hasConcept C41008148 @default.
- W2966567766 hasConcept C62611344 @default.
- W2966567766 hasConcept C66938386 @default.
- W2966567766 hasConcept C80444323 @default.
- W2966567766 hasConcept C81363708 @default.
- W2966567766 hasConceptScore W2966567766C114614502 @default.
- W2966567766 hasConceptScore W2966567766C127413603 @default.
- W2966567766 hasConceptScore W2966567766C132525143 @default.
- W2966567766 hasConceptScore W2966567766C154945302 @default.
- W2966567766 hasConceptScore W2966567766C184720557 @default.
- W2966567766 hasConceptScore W2966567766C199845137 @default.
- W2966567766 hasConceptScore W2966567766C31258907 @default.
- W2966567766 hasConceptScore W2966567766C33923547 @default.
- W2966567766 hasConceptScore W2966567766C41008148 @default.
- W2966567766 hasConceptScore W2966567766C62611344 @default.
- W2966567766 hasConceptScore W2966567766C66938386 @default.
- W2966567766 hasConceptScore W2966567766C80444323 @default.
- W2966567766 hasConceptScore W2966567766C81363708 @default.
- W2966567766 hasLocation W29665677661 @default.
- W2966567766 hasOpenAccess W2966567766 @default.
- W2966567766 hasPrimaryLocation W29665677661 @default.
- W2966567766 hasRelatedWork W1856617497 @default.
- W2966567766 hasRelatedWork W2041126748 @default.
- W2966567766 hasRelatedWork W2071483494 @default.
- W2966567766 hasRelatedWork W2104386080 @default.
- W2966567766 hasRelatedWork W2162982837 @default.
- W2966567766 hasRelatedWork W2355549421 @default.
- W2966567766 hasRelatedWork W2785918180 @default.
- W2966567766 hasRelatedWork W2963630426 @default.
- W2966567766 hasRelatedWork W335527655 @default.
- W2966567766 hasRelatedWork W4312405462 @default.
- W2966567766 isParatext "false" @default.
- W2966567766 isRetracted "false" @default.
- W2966567766 magId "2966567766" @default.
- W2966567766 workType "article" @default.