FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220808225> ?p ?o ?g. }

• W4220808225 endingPage "108538" @default.
• W4220808225 startingPage "108538" @default.
• W4220808225 abstract "Node classification for highly imbalanced graph data is challenging, with existing graph neural networks (GNNs) typically utilizing a balanced class distribution to learn node embeddings on graph data. However, when dealing with an imbalanced class distribution, they tend to bias the nodes of the majority classes while the nodes of the minority classes are under-represented. To overcome this challenge, this work introduces a novel GNN-based Imbalanced Node Classification Model (GNN-INCM) that is appropriate for class-imbalanced graph data, comprising two cooperative modules: Embedding Clustering-based Optimization (ECO) and Graph Reconstruction-based Optimization (GRO). ECO first employs a two-layer graph convolutional network (GCN) to obtain node embeddings and then performs clustering analysis to enhance the representative nature of the node embeddings and ease classification. Moreover, GRO employs an inner product decoder to reconstruct graph structure and minimize information loss. In particular, we design a hard sample strategy and integrate it into ECO and GRO to ensure that the embeddings of the hard nodes are correctly represented. Furthermore, we propose a Hard Sample-based Knowledge Distillation Method (HSKDM) to train multiple GNN-INCM models simultaneously and improve the overall classification performance. Experiments on three well-known class-imbalanced graph datasets demonstrate that GNN-INCM outperforms current state-of-the-art methods in node classification tasks and that HSKDM can substantially improve the overall classification performance." @default.
• W4220808225 created "2022-04-03" @default.
• W4220808225 creator A5049015061 @default.
• W4220808225 creator A5081537657 @default.
• W4220808225 creator A5091663194 @default.
• W4220808225 date "2022-05-01" @default.
• W4220808225 modified "2023-10-13" @default.
• W4220808225 title "A graph neural network-based node classification model on class-imbalanced graph data" @default.
• W4220808225 cites W1496056137 @default.
• W4220808225 cites W1993220166 @default.
• W4220808225 cites W2022477494 @default.
• W4220808225 cites W2107686700 @default.
• W4220808225 cites W2132791018 @default.
• W4220808225 cites W2147555557 @default.
• W4220808225 cites W2148143831 @default.
• W4220808225 cites W2393319904 @default.
• W4220808225 cites W2440599146 @default.
• W4220808225 cites W2531607313 @default.
• W4220808225 cites W2551429935 @default.
• W4220808225 cites W2558460151 @default.
• W4220808225 cites W2620998106 @default.
• W4220808225 cites W2798869704 @default.
• W4220808225 cites W2896206046 @default.
• W4220808225 cites W2914361121 @default.
• W4220808225 cites W2936503027 @default.
• W4220808225 cites W2950697450 @default.
• W4220808225 cites W2962914239 @default.
• W4220808225 cites W2963351448 @default.
• W4220808225 cites W2963469976 @default.
• W4220808225 cites W2963691377 @default.
• W4220808225 cites W2964732194 @default.
• W4220808225 cites W2966028836 @default.
• W4220808225 cites W2999127310 @default.
• W4220808225 cites W3010726750 @default.
• W4220808225 cites W3010882522 @default.
• W4220808225 cites W3012519163 @default.
• W4220808225 cites W3023532456 @default.
• W4220808225 cites W3030030520 @default.
• W4220808225 cites W3035286001 @default.
• W4220808225 cites W3038003025 @default.
• W4220808225 cites W3041664846 @default.
• W4220808225 cites W3081987387 @default.
• W4220808225 cites W3089944807 @default.
• W4220808225 cites W3092504984 @default.
• W4220808225 cites W3104097132 @default.
• W4220808225 cites W3105705953 @default.
• W4220808225 cites W3111732345 @default.
• W4220808225 cites W3112701542 @default.
• W4220808225 cites W3120683583 @default.
• W4220808225 cites W3134789204 @default.
• W4220808225 cites W3134867609 @default.
• W4220808225 cites W3136640655 @default.
• W4220808225 cites W3154252594 @default.
• W4220808225 cites W4205581758 @default.
• W4220808225 cites W4210257598 @default.
• W4220808225 doi "https://doi.org/10.1016/j.knosys.2022.108538" @default.
• W4220808225 hasPublicationYear "2022" @default.
• W4220808225 type Work @default.
• W4220808225 citedByCount "16" @default.
• W4220808225 countsByYear W42208082252022 @default.
• W4220808225 countsByYear W42208082252023 @default.
• W4220808225 crossrefType "journal-article" @default.
• W4220808225 hasAuthorship W4220808225A5049015061 @default.
• W4220808225 hasAuthorship W4220808225A5081537657 @default.
• W4220808225 hasAuthorship W4220808225A5091663194 @default.
• W4220808225 hasConcept C119857082 @default.
• W4220808225 hasConcept C124101348 @default.
• W4220808225 hasConcept C127413603 @default.
• W4220808225 hasConcept C132525143 @default.
• W4220808225 hasConcept C153180895 @default.
• W4220808225 hasConcept C154945302 @default.
• W4220808225 hasConcept C41008148 @default.
• W4220808225 hasConcept C41608201 @default.
• W4220808225 hasConcept C62611344 @default.
• W4220808225 hasConcept C66938386 @default.
• W4220808225 hasConcept C73555534 @default.
• W4220808225 hasConcept C75564084 @default.
• W4220808225 hasConcept C80444323 @default.
• W4220808225 hasConceptScore W4220808225C119857082 @default.
• W4220808225 hasConceptScore W4220808225C124101348 @default.
• W4220808225 hasConceptScore W4220808225C127413603 @default.
• W4220808225 hasConceptScore W4220808225C132525143 @default.
• W4220808225 hasConceptScore W4220808225C153180895 @default.
• W4220808225 hasConceptScore W4220808225C154945302 @default.
• W4220808225 hasConceptScore W4220808225C41008148 @default.
• W4220808225 hasConceptScore W4220808225C41608201 @default.
• W4220808225 hasConceptScore W4220808225C62611344 @default.
• W4220808225 hasConceptScore W4220808225C66938386 @default.
• W4220808225 hasConceptScore W4220808225C73555534 @default.
• W4220808225 hasConceptScore W4220808225C75564084 @default.
• W4220808225 hasConceptScore W4220808225C80444323 @default.
• W4220808225 hasFunder F4320321001 @default.
• W4220808225 hasLocation W42208082251 @default.
• W4220808225 hasOpenAccess W4220808225 @default.
• W4220808225 hasPrimaryLocation W42208082251 @default.
• W4220808225 hasRelatedWork W2134482271 @default.
• W4220808225 hasRelatedWork W2601821547 @default.
• W4220808225 hasRelatedWork W3028629919 @default.

• next