FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173673281> ?p ?o ?g. }

• W3173673281 abstract "Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a small subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer from severe result quality degradation. Several existing studies make an initial effort to ease this situation, but are still far from satisfactory. In this paper, on few-labeled graph data, we propose an effective framework ABN that is readily applicable to both shallow and deep GNN architectures and significantly boosts classification accuracy. In particular, on a benchmark dataset Cora with only 1 labeled node per class, while the classic graph convolutional network (GCN) only has 44.6% accuracy, an immediate instantiation of ABN over GCN achieves 62.5% accuracy; when applied to a deep architecture DAGNN, ABN improves accuracy from 59.8% to 66.4%, which is state of the art. ABN obtains superior performance through three main algorithmic designs. First, it selects high-quality unlabeled nodes via an adaptive pseudo labeling technique, so as to adaptively enhance the training process of GNNs. Second, ABN balances the labels of the selected nodes on real-world skewed graph data by pseudo label balancing. Finally, a negative sampling regularizer is designed for ABN to further utilize the unlabeled nodes. The effectiveness of the three techniques in ABN is well-validated by both theoretical and empirical analysis. Extensive experiments, comparing 12 existing approaches on 4 benchmark datasets, demonstrate that ABN achieves state-of-the-art performance." @default.
• W3173673281 created "2021-07-05" @default.
• W3173673281 creator A5032019231 @default.
• W3173673281 creator A5039266487 @default.
• W3173673281 creator A5053780153 @default.
• W3173673281 creator A5062549536 @default.
• W3173673281 creator A5086213157 @default.
• W3173673281 date "2019-10-07" @default.
• W3173673281 modified "2023-09-27" @default.
• W3173673281 title "Effective Semi-Supervised Node Classification on Few-Labeled Graph Data" @default.
• W3173673281 cites W1533861849 @default.
• W3173673281 cites W197270748 @default.
• W3173673281 cites W2066636486 @default.
• W3173673281 cites W2097089247 @default.
• W3173673281 cites W2101210369 @default.
• W3173673281 cites W2105015213 @default.
• W3173673281 cites W2111316763 @default.
• W3173673281 cites W2111708605 @default.
• W3173673281 cites W2118045473 @default.
• W3173673281 cites W2118978333 @default.
• W3173673281 cites W2130553454 @default.
• W3173673281 cites W2149479912 @default.
• W3173673281 cites W2153959628 @default.
• W3173673281 cites W2169196724 @default.
• W3173673281 cites W2393319904 @default.
• W3173673281 cites W2440599146 @default.
• W3173673281 cites W2558460151 @default.
• W3173673281 cites W2599095274 @default.
• W3173673281 cites W2751808960 @default.
• W3173673281 cites W2809583854 @default.
• W3173673281 cites W2900763475 @default.
• W3173673281 cites W2903871660 @default.
• W3173673281 cites W2918342466 @default.
• W3173673281 cites W2949266350 @default.
• W3173673281 cites W2949911880 @default.
• W3173673281 cites W2952179887 @default.
• W3173673281 cites W2962756421 @default.
• W3173673281 cites W2962767366 @default.
• W3173673281 cites W2963782635 @default.
• W3173673281 cites W2963858333 @default.
• W3173673281 cites W2964015378 @default.
• W3173673281 cites W2964051675 @default.
• W3173673281 cites W2964114465 @default.
• W3173673281 cites W2964121744 @default.
• W3173673281 cites W2964282455 @default.
• W3173673281 cites W2964311892 @default.
• W3173673281 cites W2964321699 @default.
• W3173673281 cites W2964725673 @default.
• W3173673281 cites W2970971581 @default.
• W3173673281 cites W2998269939 @default.
• W3173673281 cites W2998496395 @default.
• W3173673281 cites W3028395849 @default.
• W3173673281 cites W3034492151 @default.
• W3173673281 cites W3104097132 @default.
• W3173673281 cites W3105705953 @default.
• W3173673281 cites W3120213386 @default.
• W3173673281 cites W637153065 @default.
• W3173673281 hasPublicationYear "2019" @default.
• W3173673281 type Work @default.
• W3173673281 sameAs 3173673281 @default.
• W3173673281 citedByCount "0" @default.
• W3173673281 crossrefType "posted-content" @default.
• W3173673281 hasAuthorship W3173673281A5032019231 @default.
• W3173673281 hasAuthorship W3173673281A5039266487 @default.
• W3173673281 hasAuthorship W3173673281A5053780153 @default.
• W3173673281 hasAuthorship W3173673281A5062549536 @default.
• W3173673281 hasAuthorship W3173673281A5086213157 @default.
• W3173673281 hasConcept C119857082 @default.
• W3173673281 hasConcept C124101348 @default.
• W3173673281 hasConcept C127413603 @default.
• W3173673281 hasConcept C132525143 @default.
• W3173673281 hasConcept C13280743 @default.
• W3173673281 hasConcept C154945302 @default.
• W3173673281 hasConcept C185798385 @default.
• W3173673281 hasConcept C205649164 @default.
• W3173673281 hasConcept C2776145971 @default.
• W3173673281 hasConcept C41008148 @default.
• W3173673281 hasConcept C62611344 @default.
• W3173673281 hasConcept C66938386 @default.
• W3173673281 hasConcept C80444323 @default.
• W3173673281 hasConcept C81363708 @default.
• W3173673281 hasConceptScore W3173673281C119857082 @default.
• W3173673281 hasConceptScore W3173673281C124101348 @default.
• W3173673281 hasConceptScore W3173673281C127413603 @default.
• W3173673281 hasConceptScore W3173673281C132525143 @default.
• W3173673281 hasConceptScore W3173673281C13280743 @default.
• W3173673281 hasConceptScore W3173673281C154945302 @default.
• W3173673281 hasConceptScore W3173673281C185798385 @default.
• W3173673281 hasConceptScore W3173673281C205649164 @default.
• W3173673281 hasConceptScore W3173673281C2776145971 @default.
• W3173673281 hasConceptScore W3173673281C41008148 @default.
• W3173673281 hasConceptScore W3173673281C62611344 @default.
• W3173673281 hasConceptScore W3173673281C66938386 @default.
• W3173673281 hasConceptScore W3173673281C80444323 @default.
• W3173673281 hasConceptScore W3173673281C81363708 @default.
• W3173673281 hasLocation W31736732811 @default.
• W3173673281 hasOpenAccess W3173673281 @default.
• W3173673281 hasPrimaryLocation W31736732811 @default.
• W3173673281 hasRelatedWork W1442005143 @default.
• W3173673281 hasRelatedWork W2099352187 @default.

• next