Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896043746> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2896043746 abstract "The problem of semi-supervised graph node classification is to infer the labels of unlabeled nodes based on a partially labeled graph. Graph embedding is an effective method for this problem, which utilizes the context generated by neighbors' information. Some recent approaches preserve high-order proximity to smooth the features embedded with long-range structure dependency. However, the features generated by high-order proximity may be too smooth to lost individual characteristics. To handle this problem, we propose Adaptive High-Order Graph Embedding (AHOGE), an end-to-end graph neural network that implements embedding and classification in a unified model, to retain individual details when preserving high-order proximity. Inspired by Densely Connected Convolutional Networks (DenseNets), AHOGE adaptively adopts the information of $k^{th}$ -order proximity for different $k$ , using the techniques of Highway Network. Moreover, we introduce multi-class hinge loss to deal with the hard annotated labels and class overlap. Experiments on three benchmark citation network datasets demonstrate that our approach achieves state-of-the-art performances." @default.
- W2896043746 created "2018-10-26" @default.
- W2896043746 creator A5030271803 @default.
- W2896043746 creator A5079203745 @default.
- W2896043746 date "2018-06-01" @default.
- W2896043746 modified "2023-09-24" @default.
- W2896043746 title "Semi-Supervised Classification with Adaptive High-Order Graph Embedding" @default.
- W2896043746 cites W1908728294 @default.
- W2896043746 cites W206566442 @default.
- W2896043746 cites W2090891622 @default.
- W2896043746 cites W2104290444 @default.
- W2896043746 cites W2110026675 @default.
- W2896043746 cites W2130502756 @default.
- W2896043746 cites W2139823104 @default.
- W2896043746 cites W2153579005 @default.
- W2896043746 cites W2153959628 @default.
- W2896043746 cites W2157331557 @default.
- W2896043746 cites W2271840356 @default.
- W2896043746 cites W2393319904 @default.
- W2896043746 cites W2407712691 @default.
- W2896043746 cites W2519887557 @default.
- W2896043746 cites W2962756421 @default.
- W2896043746 cites W2963446712 @default.
- W2896043746 cites W2963920355 @default.
- W2896043746 cites W3104097132 @default.
- W2896043746 doi "https://doi.org/10.1109/sera.2018.8477202" @default.
- W2896043746 hasPublicationYear "2018" @default.
- W2896043746 type Work @default.
- W2896043746 sameAs 2896043746 @default.
- W2896043746 citedByCount "0" @default.
- W2896043746 crossrefType "proceedings-article" @default.
- W2896043746 hasAuthorship W2896043746A5030271803 @default.
- W2896043746 hasAuthorship W2896043746A5079203745 @default.
- W2896043746 hasConcept C132525143 @default.
- W2896043746 hasConcept C153180895 @default.
- W2896043746 hasConcept C154945302 @default.
- W2896043746 hasConcept C41008148 @default.
- W2896043746 hasConcept C41608201 @default.
- W2896043746 hasConcept C75564084 @default.
- W2896043746 hasConcept C80444323 @default.
- W2896043746 hasConcept C81363708 @default.
- W2896043746 hasConceptScore W2896043746C132525143 @default.
- W2896043746 hasConceptScore W2896043746C153180895 @default.
- W2896043746 hasConceptScore W2896043746C154945302 @default.
- W2896043746 hasConceptScore W2896043746C41008148 @default.
- W2896043746 hasConceptScore W2896043746C41608201 @default.
- W2896043746 hasConceptScore W2896043746C75564084 @default.
- W2896043746 hasConceptScore W2896043746C80444323 @default.
- W2896043746 hasConceptScore W2896043746C81363708 @default.
- W2896043746 hasLocation W28960437461 @default.
- W2896043746 hasOpenAccess W2896043746 @default.
- W2896043746 hasPrimaryLocation W28960437461 @default.
- W2896043746 hasRelatedWork W2393319904 @default.
- W2896043746 hasRelatedWork W2787740662 @default.
- W2896043746 hasRelatedWork W2902862580 @default.
- W2896043746 hasRelatedWork W2950697450 @default.
- W2896043746 hasRelatedWork W2968345052 @default.
- W2896043746 hasRelatedWork W2985758772 @default.
- W2896043746 hasRelatedWork W2990028173 @default.
- W2896043746 hasRelatedWork W3013336437 @default.
- W2896043746 hasRelatedWork W3020597450 @default.
- W2896043746 hasRelatedWork W3026423472 @default.
- W2896043746 hasRelatedWork W3082154031 @default.
- W2896043746 hasRelatedWork W3107500918 @default.
- W2896043746 hasRelatedWork W3119579551 @default.
- W2896043746 hasRelatedWork W3135958006 @default.
- W2896043746 hasRelatedWork W3167347610 @default.
- W2896043746 hasRelatedWork W3183488132 @default.
- W2896043746 hasRelatedWork W3198982902 @default.
- W2896043746 hasRelatedWork W3199352295 @default.
- W2896043746 hasRelatedWork W3200997335 @default.
- W2896043746 hasRelatedWork W3205006230 @default.
- W2896043746 isParatext "false" @default.
- W2896043746 isRetracted "false" @default.
- W2896043746 magId "2896043746" @default.
- W2896043746 workType "article" @default.