Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902842049> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W2902842049 abstract "Recently, techniques for applying convolutional neural networks to graph-structured data have emerged. Graph convolutional neural networks (GCNNs) have been used to address node and graph classification and matrix completion. Although the performance has been impressive, the current implementations have limited capability to incorporate uncertainty in the graph structure. Almost all GCNNs process a graph as though it is a ground-truth depiction of the relationship between nodes, but often the graphs employed in applications are themselves derived from noisy data or modelling assumptions. Spurious edges may be included; other edges may be missing between nodes that have very strong relationships. In this paper we adopt a Bayesian approach, viewing the observed graph as a realization from a parametric family of random graphs. We then target inference of the joint posterior of the random graph parameters and the node (or graph) labels. We present the Bayesian GCNN framework and develop an iterative learning procedure for the case of assortative mixed-membership stochastic block models. We present the results of experiments that demonstrate that the Bayesian formulation can provide better performance when there are very few labels available during the training process." @default.
- W2902842049 created "2018-12-11" @default.
- W2902842049 creator A5005336514 @default.
- W2902842049 creator A5009031715 @default.
- W2902842049 creator A5039918531 @default.
- W2902842049 creator A5074277827 @default.
- W2902842049 date "2018-11-27" @default.
- W2902842049 modified "2023-10-17" @default.
- W2902842049 title "Bayesian graph convolutional neural networks for semi-supervised classification" @default.
- W2902842049 cites W2107107106 @default.
- W2902842049 cites W2608333859 @default.
- W2902842049 doi "https://doi.org/10.48550/arxiv.1811.11103" @default.
- W2902842049 hasPublicationYear "2018" @default.
- W2902842049 type Work @default.
- W2902842049 sameAs 2902842049 @default.
- W2902842049 citedByCount "4" @default.
- W2902842049 countsByYear W29028420492019 @default.
- W2902842049 crossrefType "posted-content" @default.
- W2902842049 hasAuthorship W2902842049A5005336514 @default.
- W2902842049 hasAuthorship W2902842049A5009031715 @default.
- W2902842049 hasAuthorship W2902842049A5039918531 @default.
- W2902842049 hasAuthorship W2902842049A5074277827 @default.
- W2902842049 hasBestOaLocation W29028420491 @default.
- W2902842049 hasConcept C107673813 @default.
- W2902842049 hasConcept C119857082 @default.
- W2902842049 hasConcept C132525143 @default.
- W2902842049 hasConcept C154945302 @default.
- W2902842049 hasConcept C2776214188 @default.
- W2902842049 hasConcept C41008148 @default.
- W2902842049 hasConcept C47458327 @default.
- W2902842049 hasConcept C80444323 @default.
- W2902842049 hasConcept C81363708 @default.
- W2902842049 hasConcept C97256817 @default.
- W2902842049 hasConceptScore W2902842049C107673813 @default.
- W2902842049 hasConceptScore W2902842049C119857082 @default.
- W2902842049 hasConceptScore W2902842049C132525143 @default.
- W2902842049 hasConceptScore W2902842049C154945302 @default.
- W2902842049 hasConceptScore W2902842049C2776214188 @default.
- W2902842049 hasConceptScore W2902842049C41008148 @default.
- W2902842049 hasConceptScore W2902842049C47458327 @default.
- W2902842049 hasConceptScore W2902842049C80444323 @default.
- W2902842049 hasConceptScore W2902842049C81363708 @default.
- W2902842049 hasConceptScore W2902842049C97256817 @default.
- W2902842049 hasLocation W29028420491 @default.
- W2902842049 hasOpenAccess W2902842049 @default.
- W2902842049 hasPrimaryLocation W29028420491 @default.
- W2902842049 hasRelatedWork W2337926734 @default.
- W2902842049 hasRelatedWork W2963958939 @default.
- W2902842049 hasRelatedWork W3021430260 @default.
- W2902842049 hasRelatedWork W3027997911 @default.
- W2902842049 hasRelatedWork W4287776258 @default.
- W2902842049 hasRelatedWork W4308353688 @default.
- W2902842049 hasRelatedWork W4312501200 @default.
- W2902842049 hasRelatedWork W4313050734 @default.
- W2902842049 hasRelatedWork W4320802194 @default.
- W2902842049 hasRelatedWork W4327499916 @default.
- W2902842049 isParatext "false" @default.
- W2902842049 isRetracted "false" @default.
- W2902842049 magId "2902842049" @default.
- W2902842049 workType "article" @default.