Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970235396> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2970235396 endingPage "15423" @default.
- W2970235396 startingPage "15413" @default.
- W2970235396 abstract "To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a key property of graph topology encoding path of various lengths. We find that GCNs are rather restrictive in learning graph moments. Without careful design, GCNs can fail miserably even with multiple layers and nonlinear activation functions. We analyze theoretically the expressiveness of GCNs, arriving at a modular GCN design, using different propagation rules. Our modular design is capable of distinguishing graphs from different graph generation models for surprisingly small graphs, a notoriously difficult problem in network science. Our investigation suggests that, depth is much more influential than width and deeper GCNs are more capable of learning higher order graph moments. Additionally, combining GCN modules with different propagation rules is critical to the representation power of GCNs." @default.
- W2970235396 created "2019-09-05" @default.
- W2970235396 creator A5038976962 @default.
- W2970235396 creator A5057778679 @default.
- W2970235396 creator A5078338477 @default.
- W2970235396 date "2019-07-11" @default.
- W2970235396 modified "2023-10-08" @default.
- W2970235396 title "Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology" @default.
- W2970235396 hasPublicationYear "2019" @default.
- W2970235396 type Work @default.
- W2970235396 sameAs 2970235396 @default.
- W2970235396 citedByCount "41" @default.
- W2970235396 countsByYear W29702353962018 @default.
- W2970235396 countsByYear W29702353962019 @default.
- W2970235396 countsByYear W29702353962020 @default.
- W2970235396 countsByYear W29702353962021 @default.
- W2970235396 crossrefType "proceedings-article" @default.
- W2970235396 hasAuthorship W2970235396A5038976962 @default.
- W2970235396 hasAuthorship W2970235396A5057778679 @default.
- W2970235396 hasAuthorship W2970235396A5078338477 @default.
- W2970235396 hasConcept C101468663 @default.
- W2970235396 hasConcept C111919701 @default.
- W2970235396 hasConcept C114614502 @default.
- W2970235396 hasConcept C132525143 @default.
- W2970235396 hasConcept C154945302 @default.
- W2970235396 hasConcept C157406716 @default.
- W2970235396 hasConcept C184720557 @default.
- W2970235396 hasConcept C203776342 @default.
- W2970235396 hasConcept C22149727 @default.
- W2970235396 hasConcept C33923547 @default.
- W2970235396 hasConcept C41008148 @default.
- W2970235396 hasConcept C59404180 @default.
- W2970235396 hasConcept C80444323 @default.
- W2970235396 hasConceptScore W2970235396C101468663 @default.
- W2970235396 hasConceptScore W2970235396C111919701 @default.
- W2970235396 hasConceptScore W2970235396C114614502 @default.
- W2970235396 hasConceptScore W2970235396C132525143 @default.
- W2970235396 hasConceptScore W2970235396C154945302 @default.
- W2970235396 hasConceptScore W2970235396C157406716 @default.
- W2970235396 hasConceptScore W2970235396C184720557 @default.
- W2970235396 hasConceptScore W2970235396C203776342 @default.
- W2970235396 hasConceptScore W2970235396C22149727 @default.
- W2970235396 hasConceptScore W2970235396C33923547 @default.
- W2970235396 hasConceptScore W2970235396C41008148 @default.
- W2970235396 hasConceptScore W2970235396C59404180 @default.
- W2970235396 hasConceptScore W2970235396C80444323 @default.
- W2970235396 hasLocation W29702353961 @default.
- W2970235396 hasOpenAccess W2970235396 @default.
- W2970235396 hasPrimaryLocation W29702353961 @default.
- W2970235396 hasRelatedWork W2116341502 @default.
- W2970235396 hasRelatedWork W2519887557 @default.
- W2970235396 hasRelatedWork W2606780347 @default.
- W2970235396 hasRelatedWork W2624431344 @default.
- W2970235396 hasRelatedWork W2805516822 @default.
- W2970235396 hasRelatedWork W2811124557 @default.
- W2970235396 hasRelatedWork W2916106175 @default.
- W2970235396 hasRelatedWork W2918342466 @default.
- W2970235396 hasRelatedWork W2950898568 @default.
- W2970235396 hasRelatedWork W2961051133 @default.
- W2970235396 hasRelatedWork W2962711740 @default.
- W2970235396 hasRelatedWork W2962810718 @default.
- W2970235396 hasRelatedWork W2963858333 @default.
- W2970235396 hasRelatedWork W2964051675 @default.
- W2970235396 hasRelatedWork W2964113829 @default.
- W2970235396 hasRelatedWork W2964114465 @default.
- W2970235396 hasRelatedWork W2964311892 @default.
- W2970235396 hasRelatedWork W2964321699 @default.
- W2970235396 hasRelatedWork W3007332492 @default.
- W2970235396 hasRelatedWork W4210257598 @default.
- W2970235396 hasVolume "32" @default.
- W2970235396 isParatext "false" @default.
- W2970235396 isRetracted "false" @default.
- W2970235396 magId "2970235396" @default.
- W2970235396 workType "article" @default.