FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999911700> ?p ?o ?g. }

• W2999911700 endingPage "333" @default.
• W2999911700 startingPage "321" @default.
• W2999911700 abstract "Deep learning methods for graph classification are critical for graph data mining. Recently, graph convolutional networks (GCNs) have been able to achieve state-of-the-art node classification. A typical process for GCNs includes two iterative steps: node feature encoding and message passing. While the former encodes each graph node independently via the uniform encoding function, the latter updates the features of each node by weighted aggregation of the features of neighboring nodes, where the weights are generated by predefined or learned graph Laplacian. However, their accuracy deteriorates for graph classification tasks because the uniform encoding function encodes all the node features involved. In this study, we propose a novel affinity-aware encoding for graph classification. In our model, we implement a separate encoding function for the neighboring nodes of each node for updating the node features, where the nodes are arranged in the order of affinity values, such as graph centrality, in order to determine the correspondence between an encoding function and a specific neighboring node. Our separate encoding function performs non-Euclidean neighboring encoding for each node by weight sharing, which enables message passing. We also develop two variants based on our separate encoding function: the graph centrality-convolutional neural network (C-CNN) and the graph centrality-graph convolutional network (C-GCN). The former performs the separate encoding function on graph data directly by the function of message passing. The latter combines the separate encoding function with the normalized graph Laplacian implemented on the graph data. Experiments demonstrate that the results obtained by our models are consistent with those obtained by classical convolutional neural networks (CNNs) on the MNIST dataset, and they outperform existing GCNs on the 20NEWS, Reuters8, and Reuters52 datasets. We also apply our two variants to online car-hailing service data for traffic congestion recognition. Our methods show state-of-the-art results compared with GCNs." @default.
• W2999911700 created "2020-01-23" @default.
• W2999911700 creator A5009180198 @default.
• W2999911700 creator A5017194230 @default.
• W2999911700 creator A5017773073 @default.
• W2999911700 creator A5044470498 @default.
• W2999911700 creator A5076983797 @default.
• W2999911700 date "2020-04-01" @default.
• W2999911700 modified "2023-10-18" @default.
• W2999911700 title "Design of affinity-aware encoding by embedding graph centrality for graph classification" @default.
• W2999911700 cites W1971421925 @default.
• W2999911700 cites W1971937094 @default.
• W2999911700 cites W1990223774 @default.
• W2999911700 cites W2076795727 @default.
• W2999911700 cites W2087391635 @default.
• W2999911700 cites W2100586428 @default.
• W2999911700 cites W2106540986 @default.
• W2999911700 cites W2112796928 @default.
• W2999911700 cites W2116341502 @default.
• W2999911700 cites W2127827747 @default.
• W2999911700 cites W2130354913 @default.
• W2999911700 cites W2132914434 @default.
• W2999911700 cites W2133131640 @default.
• W2999911700 cites W2135957668 @default.
• W2999911700 cites W2152495216 @default.
• W2999911700 cites W2160815625 @default.
• W2999911700 cites W2166681504 @default.
• W2999911700 cites W2171437346 @default.
• W2999911700 cites W2290847742 @default.
• W2999911700 cites W2519224033 @default.
• W2999911700 cites W2902886279 @default.
• W2999911700 cites W2914678061 @default.
• W2999911700 cites W2962946486 @default.
• W2999911700 cites W2963278046 @default.
• W2999911700 cites W2963912736 @default.
• W2999911700 cites W2964301648 @default.
• W2999911700 cites W2966218129 @default.
• W2999911700 cites W4239519089 @default.
• W2999911700 doi "https://doi.org/10.1016/j.neucom.2020.01.010" @default.
• W2999911700 hasPublicationYear "2020" @default.
• W2999911700 type Work @default.
• W2999911700 sameAs 2999911700 @default.
• W2999911700 citedByCount "3" @default.
• W2999911700 countsByYear W29999117002021 @default.
• W2999911700 countsByYear W29999117002023 @default.
• W2999911700 crossrefType "journal-article" @default.
• W2999911700 hasAuthorship W2999911700A5009180198 @default.
• W2999911700 hasAuthorship W2999911700A5017194230 @default.
• W2999911700 hasAuthorship W2999911700A5017773073 @default.
• W2999911700 hasAuthorship W2999911700A5044470498 @default.
• W2999911700 hasAuthorship W2999911700A5076983797 @default.
• W2999911700 hasConcept C11413529 @default.
• W2999911700 hasConcept C114614502 @default.
• W2999911700 hasConcept C125411270 @default.
• W2999911700 hasConcept C132525143 @default.
• W2999911700 hasConcept C154945302 @default.
• W2999911700 hasConcept C17169500 @default.
• W2999911700 hasConcept C19332903 @default.
• W2999911700 hasConcept C203776342 @default.
• W2999911700 hasConcept C22149727 @default.
• W2999911700 hasConcept C33923547 @default.
• W2999911700 hasConcept C41008148 @default.
• W2999911700 hasConcept C53811970 @default.
• W2999911700 hasConcept C80444323 @default.
• W2999911700 hasConceptScore W2999911700C11413529 @default.
• W2999911700 hasConceptScore W2999911700C114614502 @default.
• W2999911700 hasConceptScore W2999911700C125411270 @default.
• W2999911700 hasConceptScore W2999911700C132525143 @default.
• W2999911700 hasConceptScore W2999911700C154945302 @default.
• W2999911700 hasConceptScore W2999911700C17169500 @default.
• W2999911700 hasConceptScore W2999911700C19332903 @default.
• W2999911700 hasConceptScore W2999911700C203776342 @default.
• W2999911700 hasConceptScore W2999911700C22149727 @default.
• W2999911700 hasConceptScore W2999911700C33923547 @default.
• W2999911700 hasConceptScore W2999911700C41008148 @default.
• W2999911700 hasConceptScore W2999911700C53811970 @default.
• W2999911700 hasConceptScore W2999911700C80444323 @default.
• W2999911700 hasFunder F4320321001 @default.
• W2999911700 hasFunder F4320335774 @default.
• W2999911700 hasLocation W29999117001 @default.
• W2999911700 hasOpenAccess W2999911700 @default.
• W2999911700 hasPrimaryLocation W29999117001 @default.
• W2999911700 hasRelatedWork W1592346261 @default.
• W2999911700 hasRelatedWork W172384205 @default.
• W2999911700 hasRelatedWork W1985260677 @default.
• W2999911700 hasRelatedWork W2082417617 @default.
• W2999911700 hasRelatedWork W2405608417 @default.
• W2999911700 hasRelatedWork W2990949849 @default.
• W2999911700 hasRelatedWork W3081079206 @default.
• W2999911700 hasRelatedWork W4200283508 @default.
• W2999911700 hasRelatedWork W4251321576 @default.
• W2999911700 hasRelatedWork W4379767901 @default.
• W2999911700 hasVolume "387" @default.
• W2999911700 isParatext "false" @default.
• W2999911700 isRetracted "false" @default.
• W2999911700 magId "2999911700" @default.
• W2999911700 workType "article" @default.