Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200204476> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4200204476 endingPage "15" @default.
- W4200204476 startingPage "1" @default.
- W4200204476 abstract "Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis. One main drawback arising in most existing GCN models is that of the oversmoothing problem, i.e., the vertex features abstracted from the existing graph convolution operation have previously tended to be indistinguishable if the GCN model has many convolutional layers (e.g., more than two layers). To address this problem, in this article, we propose a family of aligned vertex convolutional network (AVCN) models that focus on learning multiscale features from local-level vertices for graph classification. This is done by adopting a transitive vertex alignment algorithm to transform arbitrary-sized graphs into fixed-size grid structures. Furthermore, we define a new aligned vertex convolution operation that can effectively learn multiscale vertex characteristics by gradually aggregating local-level neighboring aligned vertices residing on the original grid structures into a new packed aligned vertex. With the new vertex convolution operation to hand, we propose two architectures for the AVCN models to extract different hierarchical multiscale vertex feature representations for graph classification. We show that the proposed models can avoid iteratively propagating redundant information between specific neighboring vertices, restricting the notorious oversmoothing problem arising in most spatial-based GCN models. Experimental evaluations on benchmark datasets demonstrate the effectiveness." @default.
- W4200204476 created "2021-12-31" @default.
- W4200204476 creator A5017499714 @default.
- W4200204476 creator A5033632697 @default.
- W4200204476 creator A5043001105 @default.
- W4200204476 creator A5074364400 @default.
- W4200204476 creator A5079734512 @default.
- W4200204476 date "2023-01-01" @default.
- W4200204476 modified "2023-10-16" @default.
- W4200204476 title "Learning Aligned Vertex Convolutional Networks for Graph Classification" @default.
- W4200204476 doi "https://doi.org/10.1109/tnnls.2021.3129649" @default.
- W4200204476 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34890333" @default.
- W4200204476 hasPublicationYear "2023" @default.
- W4200204476 type Work @default.
- W4200204476 citedByCount "1" @default.
- W4200204476 countsByYear W42002044762023 @default.
- W4200204476 crossrefType "journal-article" @default.
- W4200204476 hasAuthorship W4200204476A5017499714 @default.
- W4200204476 hasAuthorship W4200204476A5033632697 @default.
- W4200204476 hasAuthorship W4200204476A5043001105 @default.
- W4200204476 hasAuthorship W4200204476A5074364400 @default.
- W4200204476 hasAuthorship W4200204476A5079734512 @default.
- W4200204476 hasConcept C11413529 @default.
- W4200204476 hasConcept C132525143 @default.
- W4200204476 hasConcept C154945302 @default.
- W4200204476 hasConcept C187691185 @default.
- W4200204476 hasConcept C2524010 @default.
- W4200204476 hasConcept C28723256 @default.
- W4200204476 hasConcept C33923547 @default.
- W4200204476 hasConcept C41008148 @default.
- W4200204476 hasConcept C45347329 @default.
- W4200204476 hasConcept C50644808 @default.
- W4200204476 hasConcept C80444323 @default.
- W4200204476 hasConcept C80899671 @default.
- W4200204476 hasConcept C81363708 @default.
- W4200204476 hasConceptScore W4200204476C11413529 @default.
- W4200204476 hasConceptScore W4200204476C132525143 @default.
- W4200204476 hasConceptScore W4200204476C154945302 @default.
- W4200204476 hasConceptScore W4200204476C187691185 @default.
- W4200204476 hasConceptScore W4200204476C2524010 @default.
- W4200204476 hasConceptScore W4200204476C28723256 @default.
- W4200204476 hasConceptScore W4200204476C33923547 @default.
- W4200204476 hasConceptScore W4200204476C41008148 @default.
- W4200204476 hasConceptScore W4200204476C45347329 @default.
- W4200204476 hasConceptScore W4200204476C50644808 @default.
- W4200204476 hasConceptScore W4200204476C80444323 @default.
- W4200204476 hasConceptScore W4200204476C80899671 @default.
- W4200204476 hasConceptScore W4200204476C81363708 @default.
- W4200204476 hasFunder F4320321001 @default.
- W4200204476 hasLocation W42002044761 @default.
- W4200204476 hasLocation W42002044762 @default.
- W4200204476 hasOpenAccess W4200204476 @default.
- W4200204476 hasPrimaryLocation W42002044761 @default.
- W4200204476 hasRelatedWork W2166115470 @default.
- W4200204476 hasRelatedWork W2579422054 @default.
- W4200204476 hasRelatedWork W2766296895 @default.
- W4200204476 hasRelatedWork W2806361346 @default.
- W4200204476 hasRelatedWork W3109765819 @default.
- W4200204476 hasRelatedWork W4224272151 @default.
- W4200204476 hasRelatedWork W4226487993 @default.
- W4200204476 hasRelatedWork W4230439057 @default.
- W4200204476 hasRelatedWork W4283789226 @default.
- W4200204476 hasRelatedWork W2620999375 @default.
- W4200204476 isParatext "false" @default.
- W4200204476 isRetracted "false" @default.
- W4200204476 workType "article" @default.