FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907221513> ?p ?o ?g. }

• W2907221513 abstract "This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model." @default.
• W2907221513 created "2019-01-11" @default.
• W2907221513 creator A5001982715 @default.
• W2907221513 creator A5011389990 @default.
• W2907221513 creator A5017499714 @default.
• W2907221513 creator A5048523258 @default.
• W2907221513 creator A5058540877 @default.
• W2907221513 creator A5079734512 @default.
• W2907221513 date "2018-09-04" @default.
• W2907221513 modified "2023-09-26" @default.
• W2907221513 title "A Quantum Spatial Graph Convolutional Neural Network using Quantum Passing Information." @default.
• W2907221513 cites W1429235623 @default.
• W2907221513 cites W1482568066 @default.
• W2907221513 cites W1495789144 @default.
• W2907221513 cites W1570448133 @default.
• W2907221513 cites W1576213419 @default.
• W2907221513 cites W1794977688 @default.
• W2907221513 cites W1835509607 @default.
• W2907221513 cites W1869560171 @default.
• W2907221513 cites W1879085217 @default.
• W2907221513 cites W1895577753 @default.
• W2907221513 cites W1975528636 @default.
• W2907221513 cites W1976159745 @default.
• W2907221513 cites W2002096154 @default.
• W2907221513 cites W2008857988 @default.
• W2907221513 cites W2065855908 @default.
• W2907221513 cites W2069076235 @default.
• W2907221513 cites W2139380913 @default.
• W2907221513 cites W2142498761 @default.
• W2907221513 cites W2147286743 @default.
• W2907221513 cites W2303006504 @default.
• W2907221513 cites W2393319904 @default.
• W2907221513 cites W2406128552 @default.
• W2907221513 cites W2412598452 @default.
• W2907221513 cites W2519754777 @default.
• W2907221513 cites W2745165948 @default.
• W2907221513 cites W2788919350 @default.
• W2907221513 cites W2951845198 @default.
• W2907221513 cites W2963984147 @default.
• W2907221513 cites W2964057329 @default.
• W2907221513 cites W2964311892 @default.
• W2907221513 cites W2964321699 @default.
• W2907221513 cites W637153065 @default.
• W2907221513 hasPublicationYear "2018" @default.
• W2907221513 type Work @default.
• W2907221513 sameAs 2907221513 @default.
• W2907221513 citedByCount "0" @default.
• W2907221513 crossrefType "posted-content" @default.
• W2907221513 hasAuthorship W2907221513A5001982715 @default.
• W2907221513 hasAuthorship W2907221513A5011389990 @default.
• W2907221513 hasAuthorship W2907221513A5017499714 @default.
• W2907221513 hasAuthorship W2907221513A5048523258 @default.
• W2907221513 hasAuthorship W2907221513A5058540877 @default.
• W2907221513 hasAuthorship W2907221513A5079734512 @default.
• W2907221513 hasConcept C132525143 @default.
• W2907221513 hasConcept C154945302 @default.
• W2907221513 hasConcept C41008148 @default.
• W2907221513 hasConcept C80444323 @default.
• W2907221513 hasConcept C81363708 @default.
• W2907221513 hasConceptScore W2907221513C132525143 @default.
• W2907221513 hasConceptScore W2907221513C154945302 @default.
• W2907221513 hasConceptScore W2907221513C41008148 @default.
• W2907221513 hasConceptScore W2907221513C80444323 @default.
• W2907221513 hasConceptScore W2907221513C81363708 @default.
• W2907221513 hasLocation W29072215131 @default.
• W2907221513 hasOpenAccess W2907221513 @default.
• W2907221513 hasPrimaryLocation W29072215131 @default.
• W2907221513 hasRelatedWork W2784055555 @default.
• W2907221513 hasRelatedWork W2788919350 @default.
• W2907221513 hasRelatedWork W2794873889 @default.
• W2907221513 hasRelatedWork W2891082150 @default.
• W2907221513 hasRelatedWork W2893184686 @default.
• W2907221513 hasRelatedWork W2899922526 @default.
• W2907221513 hasRelatedWork W2917992855 @default.
• W2907221513 hasRelatedWork W2919603742 @default.
• W2907221513 hasRelatedWork W2963278046 @default.
• W2907221513 hasRelatedWork W2972933289 @default.
• W2907221513 hasRelatedWork W2998423439 @default.
• W2907221513 hasRelatedWork W3012774908 @default.
• W2907221513 hasRelatedWork W3028917156 @default.
• W2907221513 hasRelatedWork W3047609316 @default.
• W2907221513 hasRelatedWork W3093002101 @default.
• W2907221513 hasRelatedWork W3095213891 @default.
• W2907221513 hasRelatedWork W3155164980 @default.
• W2907221513 hasRelatedWork W3189078958 @default.
• W2907221513 hasRelatedWork W3191299186 @default.
• W2907221513 hasRelatedWork W3197871390 @default.
• W2907221513 isParatext "false" @default.
• W2907221513 isRetracted "false" @default.
• W2907221513 magId "2907221513" @default.
• W2907221513 workType "article" @default.